Parbhat Kapila
AI Systems Engineer · Bengaluru
Open to work
I build AI systems that know when not to act. Most of my work is RAG and LLM infrastructure - retrieval, vector storage, and model routing. I own the whole thing: decisions, features, deploys, monitoring, and the stuff that breaks after launch.
Right now I run five AI products in production, with no team behind them: Sentinel, Cutline, RepoDoc, VectorMail and Visura. I built every layer of every one, and I'm the only person on call for them. Cutline has been running since March: 81 signups, all inbound, and a first paying customer in September, with no ads run.
I'm looking for a full-time, early-stage role where I own real systems and deliver without hand-holding, fully remote and flexible across US/EU hours. Hand me the problem and the constraints, and I'll take it from design through deploy and on-call. I reply within 24 hours to anything real. Say hello.
- Frontend (Product UI)
- TypeScript · React · Next.js (App Router) · Tailwind CSS · Remotion
- Backend & APIs
- Node.js · tRPC · Zod · WebSockets · Dodo Payments · Clerk · Better Auth
- AI Systems (Production)
- OpenAI · Claude · Gemini · OpenRouter · RAG pipelines · pgvector
- Data & Infrastructure
- PostgreSQL · Prisma · Redis · BullMQ · Object Storage (S3)
- Cloud & Deployment
- AWS · Docker · Vercel · CI/CD (GitHub Actions)
- Architecture & Practices
- Distributed systems · Event-driven design · Multi-tenant SaaS · Cost optimization
Walkthroughs
Walkthroughs I recorded on Loom for Sentinel, Cutline, RepoDoc and VectorMail, each 11 to 14 minutes long. Open any one to watch.
1,418 contributions in 2026Verify on GitHub ↗
Experience
Founder & AI Systems EngineerIndependent / Engineering for early-stage startups · Remote2025 - PresentFull ownership of system design, feature delivery, reliability, and iteration - everything here built, deployed, and maintained by me.
Owned backend services, data stores, AI pipelines, and deployment infrastructure, including authentication, payments, and third-party integrations. Debugged production incidents, performance bottlenecks, and scaling limits while deploying continuously without breaking live systems.
- Next.js
- TypeScript
- PostgreSQL
- Redis
- OpenAI
- pgvector
- Docker
- AWS
Thanks for scrolling all the way down here. I'm open to full-time remote roles at early-stage, AI-first startups. If that's you, let's work together.
Parbhat Kapila
Rather talk it through? Book a 15-min call