Shopify
Autonomous Billing Proxy
Billing agents only after a useful response.
Separates response delivery from verification, then commits the wallet debit and ledger entry in one Postgres transaction.
Read case study Architecture · decisions · evidenceIshaan
Saraswat
I work on developer tools, distributed systems, and applied machine learning.
01 / PROJECTS
Selected projects
Distributed Vector Database
A distributed ANN engine built from the index up.
Implemented HNSW search, SIMD distance kernels, hash-routed writes, and global top-k aggregation in C++20.
Read case study Architecture · decisions · evidenceLiftCircle
Connecting workout history to useful coaching.
Combines structured workout logs and retrieved training context in a native iOS experience, with evaluation for the coaching backend.
Read case study Architecture · decisions · evidence02 / WORK & RESEARCH
Experience
Internships and research in machine learning, agent evaluation, and software engineering.
View experienceShopifyLATESTMachine Learning Engineer InternSep — Dec 2026
ML-assisted code understanding and debugging.
Developing Binks, Shopify’s code debugging tool. My work spans automated code understanding, bug diagnosis, and evaluation of ML-powered debugging assistance for developers.
Bellevue, WA
IBMSoftware Engineer InternJun — Sep 2026
Agent evaluation and API routing verification.
Designed verification systems across 100+ enterprise workflow scenarios. Hardened Tool Manager API routing with sub-200ms validation latency and built test environments for a system designed for 10,000+ daily agent invocations.
Silicon Valley Labs · San Jose, CA
Shah Lab · UCLAUndergraduate ML Research AssistantSep 2025 — Mar 2026
Embryo segmentation with deep learning.
Engineered ML pipelines and deep learning models on approximately 500,000 microscopy frames for embryo segmentation. Optimized models beyond the 95% accuracy baseline to support developmental biology and neuronal circuit analysis.
Los Angeles, CA
App-ScoopSoftware Engineering InternJun — Sep 2025
AI automation and full-stack development.
Co-developed an AI automation platform that boosted user presence scores by up to 40%. Improved dashboard productivity by 20%, deployed a Dockerized inference microservice, and established GitHub Actions CI/CD pipelines.
San Francisco, CA
03 / INTERACTIVE VECTOR SEARCH
What makes a
close match?
Vector databases retrieve items by similarity. Move the query to see which stored vectors are closest, and how the top three results change.
- 01 Move the query point.
- 02 Compare Euclidean distances.
- 03 Keep the nearest three vectors.
This exact 2D search illustrates the idea. My C++ database uses an approximate HNSW index for 768-dimensional vectors and merges results across shards.
Inside the vector databaseFROM MY VECTOR DATABASE PROJECT
Find the nearest vectors
Move the query point to see its three closest matches.
QUERY
NEAREST MATCHESEUCLIDEAN DISTANCE
- 1v250.067
- 2v270.114
- 3v350.156
A 2D demo using sample data. My database searches 768-dimensional vectors with an HNSW index.
View the C++ database project
UCLA · LOS ANGELES, CA04 / ABOUT
About me
I’m a Computer Science & Engineering student at UCLA, graduating in June 2028. My experience includes ML-assisted debugging at Shopify, agent evaluation at IBM, and computer vision research at Shah Lab. I’m especially interested in infrastructure that makes ML fast, reliable, and useful to developers.
Outside of work and school, I enjoy weightlifting, basketball, and trying restaurants around LA.
Download résumé05 / CONTACT
Contact
Fill out this form, or email me at
For engineering roles, projects, or research.