Summary
Full-stack engineer with nearly 2 years of experience building production web applications and AI products using React, Next.js, Node.js, PostgreSQL, RAG, and agent workflows. Comfortable owning features end to end, from development to deployment.
Skills
- Languages: TypeScript, JavaScript
- Frontend: React, Next.js, TanStack Query, Zustand
- Backend: Node.js, Express.js, PostgreSQL, MongoDB, Redis, Docker, AWS
- ORMs: Prisma, Drizzle Vector DBs: pgvector, Pinecone, Qdrant
- AI/LLM: RAG pipelines, LangGraph, LangChain, Agentic tool orchestration
Experience
- Led Bonkers end-to-end v2-to-v3 migration, unifying recreation, regeneration, and editing workflows into a single image-to-image pipeline, delivering daily stability improvements and weekly UX features, contributing to a 50% increase in DAU post-migration.
- Developed Templates feature, enabling one-click generation of high-quality images across multiple styles and use cases, simplifying the creation process and resulting in 20K+ images generated in the first month.
- Spearheaded a full-scale refactor of Merlin-Chat, improving codebase readability, modularity, and maintainability through component abstraction and memoization, resolved critical memory leaks and boosted the Lighthouse score from 30 to 90+.
- Built automated code-generation tool for event tracking, analyzing developer workflows to create solutions that reduced manual implementation time by 70%.
- Contributed to deployment infrastructure overhaul designing scalable platform architecture that achieved 3x faster deployment cycles with reduced production incidents.
- Created internal monitoring dashboard for service health management, implementing real-time alerting system that cut incident resolution time by 50%.
Projects
- Designed run admission for a prompt-to-production builder: Postgres advisory locks enforce global, per-user, and per-chat limits before a BullMQ worker begins work.
- Made generation resumable by persisting typed stream events in an append-only log. Reconnecting clients replay missed file, tool, build, and preview state instead of restarting a run.
- Isolated generated-code execution in per-chat Docker sandboxes with Redis-coordinated provisioning, resource and network limits, and an export path to S3-backed previews.
- Routed each chat turn across direct answers, document retrieval, memory, semantic cache, and connected tools only after ownership, API-key, and context-budget checks.
- Built a document-answer path with safe ingest, token-aware chunking, pgvector search, lexical fallback, reranking, and isolated document context from agent instructions.
- Built approval-gated LangGraph workflows for destructive connector actions. Durable checkpoints persist stream state so chats resume after browser refreshes or interrupted tool calls.
Education
B.Tech in Information Technology (7.6 CGPA)