Parbhat Kapila · Full-Stack Engineer
Full-stack engineer focused on internal AI tools, RAG infrastructure, and data-heavy SaaS. I ship from zero to live product, then keep it fast, cheap, and reliable under real traffic.
Full-stack & AI projects serving real users, with measurable business impact.
Detects deals that are starting to stall before it's visible in a CRM. It models time decay, stage velocity, and engagement signals from live pipeline data. Fast, explainable, and designed for real integration load.
Automated code documentation system processing 200+ repositories and 100K+ LOC. Reduced onboarding time by 75% with 92% relevance accuracy, serving engineering teams at scale.
Knowledge operations system processing 10k+ documents with 94%+ accuracy. Reduced processing costs significantly through intelligent architecture, achieving 50–80% AI cost savings via chunk reuse.
TypeScript, React, Next.js (App Router), Tailwind CSS
Node.js, Python, FastAPI, Express.js, REST APIs, WebSockets
OpenAI / GPT-4, LangChain, RAG pipelines, pgvector, embedding search, LLM orchestration
PostgreSQL, Redis, Object Storage (S3), queues / async processing
AWS (EC2, S3, RDS), Docker, Vercel, CI/CD (GitHub Actions)
Multi-tenant SaaS, distributed systems, event-driven design, system design, performance optimization
Designing scalable, production-grade systems from the ground up. Built multi-tenant SaaS architectures with isolated data models, auto-scaling infrastructure for real production workloads, and cost-optimized deployments driven by architectural tradeoffs, reducing infrastructure spend by 95% without sacrificing reliability.
Productionized LLM and RAG systems backed by vector databases at scale. Built retrieval pipelines processing 10,000+ documents with 94%+ accuracy, optimized pgvector queries for sub-200ms latency, and implemented multi-provider LLM orchestration with GPT-4 and resilient fallback strategies.
Driving measurable business impact through technical optimization. Reduced per-document processing costs from $5.00 to $0.05 through architectural changes and chunk reuse, achieved sub-200ms semantic search latency under load, and maintained 99.9% uptime across live production systems.
Building and operating production systems used by real users daily. Independently responsible for technical decisions, feature delivery, deployments, monitoring, and post-launch reliability across TypeScript, Next.js, Python, PostgreSQL, Redis, AWS, and Vercel. Owning systems from first commit through live operation.
I'm an AI-focused full-stack engineer building production systems used by real teams. Over the past three years, I've shipped and operated live products handling large data volumes and reduced operational costs by 95%.
I specialize in turning complex AI pipelines into reliable software retrieval, vector storage, and model orchestration optimized for low latency (sub-200ms), high accuracy (94%+), and real production constraints.
I'm seeking a full-time role at a startup where execution matters and engineers are trusted to ship systems that deliver measurable business value.
Independent Product Development
Built, shipped, and operated multiple production AI products used by real teams. Took full responsibility for system design, feature delivery, reliability, and iteration driven by live usage across independently run SaaS applications.
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 shipping improvements continuously without breaking live systems.
Open to full-time remote engineering roles at US startups building production AI systems. Best fit for teams that value ownership, speed, and engineers who ship and maintain what they build. Comfortable aligning with US time zones and working directly with founders in fast-moving environments.
Let's build together
Available for roles & projects