Ketul Kishorbhai Chhaya
AI-focused backend engineer. Architected BizChat, an LLM platform serving 220+ Baltimore entrepreneurs via the Mayor's Office, with routing across Bedrock/OpenAI/Anthropic and an open-source observability package.
Experience
Software Engineer – Platform & AI
BizChat- Reduced Firestore reads by 108x (2,800 to 26 per query) by building an inverted index, rebuilt weekly by a scheduled Cloud Run function that uses content hashing to update only changed records, and served through a Next.js API.
- Shipped a multi-provider model router adopted by 64% of active users, enabling zero-loss mid-session switching across OpenAI, Claude, Mistral, and Llama via Firebase persistence.
- Engineered a TypeScript/Firestore pipeline aggregating 100K+ telemetry events into human-AI collaboration metrics, surfaced via a React dashboard for a CHI publication.
- Reduced monthly LLM costs by migrating a scraping workload that drove 40% of token spend, identified via a self-built open-source TypeScript proxy, tokenwise-tracker.
- Built a streaming AI edit pipeline in TypeScript, Next.js, and AWS Bedrock, where the LLM emits NDJSON ops against a custom ProseMirror section schema, replacing a 700-line fuzzy matcher.
- Automated an end-to-end Playwright test suite covering the full user journey across Chromium, Firefox, and WebKit, with Slack alerts and report links that caught regressions before production.
Software Engineer
Aavenir- Reduced contract migration time from two weeks to five days by building Python ETL pipelines and Spring Boot REST services, processing 8,000+ contracts with AI-driven metadata extraction.
- Prevented 6+ concurrent redlining collisions on shared contracts with a JavaScript webhook based locking and presence system between the Office.js Word add-in and ContractFlow portal.
- Designed a Spring Boot provisioning service using dependency injection and modular service abstractions to aggregate configuration across client environments, saving 100+ engineering hours across 4 deployments.
- Scaled a NestJS approval microservice to route contracts through parallel or sequential approver chains by value, cutting approval turnaround 50% over the prior manual process.
- Implemented an AngularJS admin console to configure approvals, triggers, delegations, and audit timelines, cutting manual workflow effort 35%.
Full Stack Engineer Intern
ClosestCloset- Optimized MongoDB ranking API from 5s to 800ms by precomputing and caching scores via Node.js cron job, reducing query latency by 84%.
- Launched a real-time Node.js chat service on Azure Web PubSub with a React client linking buyers and sellers, with email fallback for offline users, cutting order-status support tickets by 40%.
- Built internal CMS in React, Express, and MongoDB enabling marketing to self-publish campaign pages and edit site content, eliminating 12 engineering tickets per week.
Projects
Building a LangGraph and Temporal pipeline that crawls sites into pgvector, probes Claude/GPT/Gemini in parallel on buyer intent questions, and scores brand visibility via cosine similarity gaps with sourced fixes.
Designed a fault-tolerant, event-driven payment pipeline (FastAPI, Kafka) achieving exactly-once processing guarantees via Redis SETNX idempotency keys, with exponential backoff retries and a dead-letter queue to isolate failures.
Built a TypeScript MCP server that parses a codebase into an import dependency graph, helping AI agents catch circular imports that break builds and trace what a file change affects across 1,448 files in 1.1s.
Designed a TypeScript production-scheduling engine that reflows orders around delays and maintenance windows via Kahn's topological sort and greedy shift-aware placement, covered by 16 Vitest cases.