{ "generatedAt": "2026-03-30T04:40:29.235Z", "site": { "owner": "Shiv Jhalani", "focusAreas": [ "Software Engineer @ INRIX", "Backend • Data • Product" ], "note": "* P.S. I just love using em-dashes, I promise it’s not what it looks like." }, "hero": { "kicker": "Hi, I’m", "name": "Shiv Jhalani", "paragraphs": [ "Hi, I’m Shiv Jhalani — a backend-focused software engineer at INRIX with a strong interest in data, product engineering, and modern AI-driven systems.", "I’m motivated by curiosity and learn best by building: from experimenting with embeddings and search, to prototyping agentic AI systems, to shipping data-heavy features and services in production. I enjoy working with new ideas, new tools, and new technologies, and turning them into real, working products.", "I use modern AI tools as part of my workflow — not as a shortcut, but as leverage. I care about shipping faster, iterating intelligently, and then applying strong fundamentals to make the result correct, reliable, and maintainable.", "What keeps me motivated is how quickly this field evolves. I have a constant need to keep up — new tools, new approaches, new ideas — and I enjoy turning that motion into real projects that solve real problems. I’m always building, always learning, and always looking for the next interesting problem to dive into." ] }, "now": { "learning": [ { "id": "agentic-commerce-protocol", "title": "Agentic Commerce Protocol (ACP)", "summary": "Documenting how ACP boils down to four merchant-side API calls that publish inventory, receive intents, quote orders, and settle—surprisingly approachable.", "tag": "Agentic Systems", "updatedAtISO": "2025-01-15T12:00:00.000Z", "note": "Cool realization: the merchant integration really is just four API calls." }, { "id": "transformer-black-box", "title": "Transformers, attention, and the LLM black box", "summary": "Getting into the weeds of how the query vector interacts with K and V to reshape a token’s embedding during attention.", "tag": "Deep Learning", "updatedAtISO": "2025-01-14T12:00:00.000Z", "note": "Tracing the Q·K softmax and how the weighted V updates each word." }, { "id": "x402-machine-payments", "title": "x402 and machine payments", "summary": "Exploring x402 as a payment primitive for agent-driven commerce, where software can discover services, transact, and settle value on its own.", "tag": "Agentic Commerce", "updatedAtISO": "2026-03-15T12:00:00.000Z", "note": "Agent-driven commerce feels especially exciting in a world where agents keep getting more capable." } ], "readingQueue": [ { "id": "greenlights", "title": "Greenlights", "kind": "book", "authorOrSource": "Matthew McConaughey", "status": "in_progress", "note": "Didn’t realize he was on the law-school track. Awed by his humility the first time he dealt with fame." }, { "id": "ddia", "title": "Designing Data-Intensive Applications", "kind": "book", "authorOrSource": "Martin Kleppmann", "status": "in_progress", "note": "Replicas are more than copies—leaders, followers, and lag windows all add gnarly coordination issues I took for granted." }, { "id": "dwarkesh", "title": "The Dwarkesh Podcast", "kind": "podcast", "authorOrSource": "Dwarkesh Patel", "status": "in_progress", "note": "Currently on the Andrej Karpathy episode—loved his breakdown of how AI co-pilots reshaped his day-to-day workflow." }, { "id": "how-i-built-this", "title": "How I Built This", "kind": "podcast", "authorOrSource": "Guy Raz", "status": "in_progress", "note": "Favorite takeaway: every single founder seems to be doubted right before their inflection point." } ], "githubSummary": { "mostActiveHour": "8 PM–9 PM PT", "languages": "Python, TypeScript, Jupyter Notebook", "focus": "Shipping agentic-tool-registry + portfolio", "siteLastUpdated": "Mar 17, 2026", "siteLastChange": "update learnings" }, "personalityHighlights": [ { "id": "cooking", "title": "Home Chef", "description": "Cooking lets me unplug, experiment with flavor, and share something tangible with the people I care about.", "details": "I’ll chase fancy plating one night and crave simple comfort food the next—but the through-line is cooking for others. I love recreating restaurant dishes to understand every step, then sharing the results with friends and family.", "image": { "src": "/images/hobbies/food2.jpeg", "alt": "Cooking a favorite recipe" } }, { "id": "golf", "title": "Weekend Golfer", "description": "Golf is my reset button and the newest obsession I’m trying to level up.", "details": "I’m still new, but I’m hooked on the pursuit of that one flushed shot that lands pin-high. It’s wild how hard a stationary ball can be to hit—perfect practice in patience and iteration. Fun fact: I just carded a hole-in-one on a 205-yard par 3 by absolutely flushing a 4i, then immediately called everyone I’ve ever golfed with!", "image": { "src": "/images/hobbies/golf.jpeg", "alt": "On the course" } }, { "id": "badminton", "title": "Badminton Regular", "description": "Quick rallies, quicker decisions (plus the lifting sessions that keep me ready for them).", "details": "I grew up playing competitively, so it’s still my go-to for high-intensity cardio. Weekly doubles plus strength work keep the timing, positioning, and explosive movement dialed in.", "image": { "src": "/images/hobbies/badminton.png", "alt": "Badminton court" } } ] }, "collections": { "workExperience": [ { "id": "inrix-backend-2025", "title": "Backend Software Engineer", "organization": "INRIX", "organizationNote": "INRIX is one of the longest-running traffic intelligence providers, ingesting global mobility data streams.", "timeframe": "Aug 2025 – Present", "summary": "Delivering mobility data solutions across high-performance Python, Java, and AWS services.", "bullets": [ "Develop & optimize high-performance APIs & software solutions using Python, Java, and AWS to deliver mobility data solutions", "Architect & integrate scalable data processing workflows to enable new customer-facing features while maintaining existing systems with focus on clean code & CI/CD best practices, while maintaining cost efficiency across cloud-native environments" ], "tags": [ "Python", "Java", "AWS", "APIs", "CI/CD" ], "media": [ { "src": "/images/INRIXlogo.png", "alt": "INRIX logo", "variant": "logo" } ], "links": [ { "label": "Talk about my work at INRIX so far", "href": "https://example.com/work/inrix-backend" } ] }, { "id": "inrix-intern-2024", "title": "Backend Software Engineering Intern", "organization": "INRIX", "organizationNote": "INRIX is one of the longest-running traffic intelligence providers, ingesting global mobility data streams.", "timeframe": "Jun 2024 – Sep 2024", "summary": "Focused on SafetyView API efficiency and modernization across Python/Java services.", "bullets": [ "Enhanced efficiency of customer-facing API using Python, Java, & AWS technologies, cutting costs by 30%-90%", "Upgraded legacy code to modern versions to improve performance & maintainability while ensuring backward compatibility" ], "tags": [ "Java", "Python", "AWS", "Serverless", "Optimization" ], "media": [ { "src": "/images/INRIXlogo.png", "alt": "INRIX brand artwork", "variant": "logo" } ], "links": [ { "label": "Talk about my time at INRIX (Summer 2024)", "href": "mailto:shivjhalani@gmail.com?subject=SafetyView%20pipeline%20details" } ] }, { "id": "inrix-intern-2023", "title": "Software Engineering Intern", "organization": "INRIX", "organizationNote": "INRIX is one of the longest-running traffic intelligence providers, ingesting global mobility data streams.", "timeframe": "Jun 2023 – Sep 2023", "summary": "Automated SafetyView data pipelines and rallied a global hackathon team during Innovation Week.", "bullets": [ "Implemented automated multithreaded data ingestion pipeline for an internal tool using Java, Python, & AWS technologies", "Mitigated error-prone data update process, improved efficiency by 20%, deployed code to production & tested in CI/CD pipeline", "Led 11-member team to final round of company-wide hackathon, through global cross-team collaboration & project management" ], "tags": [ "Java", "Python", "AWS", "Automation" ], "media": [ { "src": "/images/INRIXlogo.png", "alt": "INRIX brand artwork", "variant": "logo" } ], "links": [ { "label": "Talk about my time at INRIX (Summer 2023)", "href": "https://example.com/work/inrix-intern-2023" } ] }, { "id": "ey-data-science", "title": "Data Science Intern", "organization": "Ernst & Young", "organizationNote": "EY is a Big Four consulting and audit firm with a large data & AI practice.", "timeframe": "Jun 2022 – Aug 2022", "summary": "Designed a voice-enabled analytics dashboard that translates natural language into SQL queries so CXO teams can self-serve insights.", "bullets": [ "Used spaCy, pandas, sent2vec, and matplotlib to interpret voice commands, generate SQL, and visualize dashboards automatically.", "Owned the project end-to-end: scoping requirements, prototyping NLP intents, and presenting the deliverable to leadership.", "Documented deployment + usage practices so other teams can build on the foundation for future analytics tools." ], "tags": [ "Python", "spaCy", "pandas", "Data Viz", "NLP" ], "media": [ { "src": "/images/ey.png", "alt": "EY dashboard concept artwork", "variant": "logo" } ], "links": [ { "label": "Talk about my time at EY", "href": "mailto:shivjhalani@gmail.com?subject=EY%20dashboard" } ] }, { "id": "ntt-summer", "title": "Summer Intern", "organization": "NTT Data Services", "organizationNote": "NTT Data Services is a global IT services company pairing enterprise clients with engineering teams.", "timeframe": "Jun 2019 – Jun 2019", "summary": "First exposure to professional data science: explored pandas/numpy/sklearn to understand how ML pipelines come together.", "bullets": [ "Built small ML experiments that combined statistical analysis, feature engineering, and model evaluation.", "Learned how production teams review code, communicate blockers, and share knowledge — a catalyst for pursuing CS at SCU." ], "tags": [ "Python", "pandas", "numpy", "sklearn" ], "media": [ { "src": "/images/ntt.png", "alt": "NTT Data internship artwork", "variant": "logo" } ], "links": [ { "label": "Talk about my time at NTT Data", "href": "mailto:shivjhalani@gmail.com?subject=NTT%20internship" } ] } ], "projectSections": [ { "id": "product-builds", "title": "Product Builds", "entries": [ { "id": "aid-agentic-advertising-platform", "title": "AID — Agentic Advertising Platform", "timeframe": "September 2025 - October 2025", "summary": "Built a backend to explore how agentic commerce and advertising could work, turning merchant product catalogs into vector-searchable listings and serving hybrid recommendations to authenticated AI agents.", "bullets": [ "Designed & implemented backend architecture using FastAPI and OpenSearch to ingest structured merchant product catalogs and serve recommendations to authenticated AI agents", "Engineered product ingestion pipeline that normalized product metadata, generated contextual embeddings via OpenAI’s Embeddings API, and indexed listings as vector-plus-metadata documents for semantic retrieval", "Built hybrid recommendation system combining OpenSearch k-NN vector search with structured filters across price, brand, category, and attributes, then reranked results using weighted semantic similarity and product completeness scores", "Implemented JWT-based affiliate tracking, impression logging, click redirects, and idempotent conversion reporting to measure downstream recommendation performance" ], "tags": [ "Python", "FastAPI", "OpenSearch", "Vector Search", "JWT" ], "links": [ { "label": "Project Demo", "href": "https://www.youtube.com/watch?v=40FzfjCIAJg" } ], "media": [ { "src": "/images/projects/aid-platform.svg", "alt": "Illustration of AID's merchant catalog ingestion, vector retrieval, and agent recommendation flow" } ] }, { "id": "ai-lecture-note-assistant", "title": "AI Lecture Note-Taking Assistant — NVIDIA GTC 2025 Golden Ticket Submission", "timeframe": "January 2025", "summary": "Backend for an AI-powered lecture companion that turns raw audio into structured Google Docs notes using speech-to-text + LLM pipelines.", "bullets": [ "Designed & implemented backend system that converts lecture audio into structured, comprehensive notes using LLM pipelines", "Engineered end-to-end workflow integrating speech-to-text, semantic summarization, and hierarchical note structuring synced with Google Docs", "Built scalable API-based architecture to process long-form lectures while preserving key concepts, examples, and context", "Positioned tool for dual-use by students and professors to improve accessibility, retention, and material distribution" ], "tags": [ "Python", "LLM", "Speech-to-Text", "APIs" ], "links": [ { "label": "Project Demo", "href": "https://www.youtube.com/watch?v=ZSaw7HFSVjk" } ], "media": [ { "src": "/images/projects/nvidia.png", "alt": "Screenshot from NVIDIA AI lecture assistant demo" } ] }, { "id": "post-filtering-extension", "title": "Post Filtering Extension — 1st Place Winner, xAI Hackathon (Replit Award)", "timeframe": "October 2024", "summary": "Chrome extension that filters engagement farmers, self-promoters, and bots on X using Grok 2 / xAI APIs.", "bullets": [ "Designed & implemented backend architecture of Chrome extension that filters out engagement farmers, self-promoters, & bots on X using Grok 2 LLM and xAI APIs, fostering relevant and meaningful conversations", "Integrated X APIs to retrieve and process posts in a streaming architecture, enabling incremental data delivery & reduced latency" ], "tags": [ "Python", "LLM", "xAI" ], "links": [ { "label": "xAI/Replit Feature & Demo", "href": "https://x.com/replit/status/1847043212667670667?s=46&t=h62ESz3AaX2SW8S3sfnqcw" } ], "media": [ { "src": "/images/projects/grok.png", "alt": "Post filtering extension" } ] }, { "id": "academic-support-platform", "title": "Academic Support Platform — Google Gemini API Developer Competition Submission", "timeframe": "August 2024", "summary": "Backend for a Gemini-powered academic assistant that simplifies registration and real-time support.", "bullets": [ "Engineered backend architecture of web application designed to enhance academic life by simplifying course registration & providing real-time academic support using Python, Flask, & effective prompt engineering for Google’s Gemini API", "Utilized Google’s Gemini API to develop AI-driven Virtual Tutor & Academic Advisor tools for personalized student assistance", "Integrated Firebase for secure data storage & efficient management of chat histories, ensuring reliable app performance" ], "tags": [ "Python", "Flask", "Gemini", "Firebase" ], "links": [ { "label": "Project Demo", "href": "https://www.youtube.com/watch?v=BVtw-ZKlJEM" } ], "media": [ { "src": "/images/projects/gemini.png", "alt": "Academic support platform" } ] }, { "id": "career-fair-automation", "title": "Career Fair Data Analysis Automation", "timeframe": "April 2023", "summary": "Automated the Santa Clara career center’s fair analytics workflow so peer advisors could see student + employer trends without spending a week inside Excel.", "bullets": [ "Developed Python program using pandas library to automate the data analysis process for career fairs, providing quick & accurate insights into student & employer trends based on demographics & feedback", "Reduced manual work & saved a week’s worth of time, increasing efficiency by 700% over 900+ rows of data" ], "tags": [ "Python", "Pandas", "Automation", "Analytics" ], "links": [ { "label": "Project Source Code", "href": "https://github.com/sjhalani7/careerfairdata" } ], "media": [ { "src": "/images/projects/career-fair.svg", "alt": "Career fair data visualization" } ] }, { "id": "health-match", "title": "Health Match — Hack4Humanity Submission", "timeframe": "February 2023", "summary": "Hack4Humanity build that pairs symptoms with AI-powered specialist recommendations using Flask + OpenAI’s DaVinci 3 API.", "bullets": [ "Designed & implemented backend architecture of Chrome extension that filters out engagement farmers, self-promoters, & bots on X using Grok 2 LLM and xAI APIs, fostering relevant and meaningful conversations", "Integrated X APIs to retrieve and process posts in a streaming architecture, enabling incremental data delivery & reduced latency" ], "tags": [ "Python", "Flask", "OpenAI", "Hackathon" ], "links": [ { "label": "View Hackathon Demo", "href": "https://devpost.com/software/appointmentaide" } ], "media": [ { "src": "/images/projects/health-match.svg", "alt": "Health Match concept art" } ] }, { "id": "tripfolio", "title": "Tripfol.io — 1st Place Winner, INRIX Hackathon @ Santa Clara University", "timeframe": "November 2022", "summary": "INRIX hackathon winner that builds optimized day-trip itineraries with a custom routing algorithm over INRIX APIs.", "bullets": [ "Designed & implemented application backend using Python, Flask, & INRIX Routing API to develop optimized routing algorithm for users that generate an itinerary based on hotspots in a geographic location", "Identified & implemented relevant graph theory to develop optimal routing algorithm in under 24 hours", "Implemented Flask API to return line strings of coordinates to enable front-end map routing on Google Maps plugin" ], "tags": [ "Python", "Flask", "INRIX APIs", "Graph Theory" ], "links": [ { "label": "View Hackathon Demo", "href": "https://devpost.com/software/bay-trips" } ], "media": [ { "src": "/images/projects/tripfolio.svg", "alt": "Tripfol.io routing visualization" } ] }, { "id": "project-pineapple", "title": "Project Pineapple — 2nd Place Winner, Hack4Humanity", "timeframe": "February 2022", "summary": "Safety-focused hack that schedules check-ins for nights out using a Python/Flask backend and SQLite storage.", "bullets": [ "Designed application backend using Python, Flask, & SQLite that uses scheduled check-ins & user verification to allow a safe night out to reduce the likelihood of sexual assaults", "Implemented an SQLite database using Python programming to store & maintain data of users effectively & systematically", "Developed an API using Flask to fetch data from database & link to the front-end software for an efficient full-stack software" ], "tags": [ "Python", "Flask", "SQLite", "Safety" ], "links": [ { "label": "View Hackathon Demo", "href": "https://devpost.com/software/project-pineapple" } ], "media": [ { "src": "/images/projects/project-pineapple.svg", "alt": "Project Pineapple graphic" } ] } ] } ], "researchProjects": [ { "id": "clickbait-detection", "title": "Clickbait Detection on Social Platforms", "organization": "Santa Clara University On-Campus Research", "timeframe": "Jan 2024 – Jun 2025", "summary": "Research assistantship exploring multi-modal topic modeling (LDA/LSA/BERTopic) and OpenAI embeddings to flag engagement-bait across two social platforms.", "bullets": [ "Collaborated with team of 2 to detect clickbait on social media through OpenAI APIs & topic modeling algorithms like LDA", "Utilized OpenAI APIs to summarize text columns, transform into vectors using sentenceTransformers library & employ cosine similarity to quantify correlation between the title & transcripts on two different datasets of a total of over 7700 rows", "Co-authored research paper detailing significant findings, presented & published at the 2024 IISA conference" ], "tags": [ "OpenAI", "LDA", "NLP", "Research" ], "links": [ { "label": "IISA 2024 publication", "href": "https://ieeexplore.ieee.org/document/10786672" } ], "media": [ { "src": "/images/research/clickbait.svg", "alt": "Clickbait detection visuals" } ] }, { "id": "hate-speech-pagerank", "title": "Online Hate Speech Spreader Detection", "organization": "Santa Clara University On-Campus Research", "timeframe": "Oct 2021 – Jan 2024", "summary": "Led a modified PageRank study that flags high-influence hate speech accounts on social networks.", "bullets": [ "Led team of 3 to detect & flag hate speech spreaders on online social networks using Python & libraries like sklearn", "Modified Google’s PageRank algorithm to implement graph-based model using adjacency matrices to calculate user influence & measure hate speech spread within user networks, enabling data & network analysis on pre-trained machine learning models", "Co-authored research paper detailing significant findings, presented & published at the 2023 International DSML conference" ], "tags": [ "Python", "Graph ML", "Sklearn", "Research" ], "links": [ { "label": "DSML 2023 paper", "href": "https://aircconline.com/csit/abstract/v13n19/csit131916.html" } ], "media": [ { "src": "/images/research/hate-speech.svg", "alt": "Hate speech research" } ] } ], "santaClaraLife": [ { "id": "leadership", "title": "Leadership & Clubs", "summary": "Poured energy into the orgs that shaped my SCU journey — scaling ACM sponsorships, mentoring peers, and amplifying entrepreneurship programs.", "bullets": [ "ACM Director of Communications: led four industry liaisons to raise $20k+ for Hack for Humanity and launched a Roblox game jam with 75 participants.", "ACM Industry Liaison: managed relationships with 10+ companies, driving $18k in sponsorships and professional development programs.", "Theta Tau Professional Development Chair: organized professional development programming for the engineering fraternity.", "Ciocca Center Student Advisory Board PR Director: shipped a bi-quarterly newsletter keeping founders informed on events and recruiting windows." ], "tags": [ "Community", "Mentorship", "Leadership" ], "media": [ { "src": "/images/santaclara/acm.png", "alt": "ACM leadership", "variant": "logo" } ] }, { "id": "awards", "title": "Awards & Honors", "summary": "Selective distinctions that recognized scholarship, leadership, and service at Santa Clara.", "bullets": [ "Student Life Award — recognized by SCU’s president as 1 of 23 seniors (out of 1,600+) improving campus life; featured in The Santa Clara’s ‘Toast to the Class of 2025 Award Winners.’", "Summa Cum Laude — graduated with SCU’s highest academic distinction", "Phi Beta Kappa — nation’s oldest arts & sciences honor society; membership extended to the top ~10% demonstrating intellectual integrity", "Upsilon Pi Epsilon — international computing honor society recognizing the top cohort of CS students for scholarship and service", "Alpha Sigma Nu — Jesuit honor society invitation reserved for <15% of the class who excel in scholarship, loyalty, and service", "University Honors Program — selective interdisciplinary cohort (~68 of 1,500 admits) focused on critical inquiry and writing" ], "tags": [ "Honors", "Awards" ], "media": [ { "src": "/images/santaclara/award.JPG", "alt": "Receiving the Student Life Award", "variant": "photo", "width": 3500, "height": 1500 } ] } ] } }