Pritam GhoshFull-Stack & AI Engineer
Software Engineer II @ Nykaa — SuperStore & GenAI
I help teams ship fast, reliable products across the stack — from React and Next.js frontends to Node.js and Go services, and production LLM/RAG systems on LangGraph. Five years turning ambiguous problems into software that scales.
- TypeScript
- Next.js
- Node.js
- Go
- LangGraph
- PostgreSQL
- AWS
- Years shipping production
- 5+Years shipping production
- Production AI features at Nykaa
- 3Production AI features at Nykaa
- Daily users · Easy Quizzz (2021–24)
- 500K+Daily users · Easy Quizzz (2021–24)
- Enterprise clients on Kaamwork SaaS
- 100+Enterprise clients on Kaamwork SaaS
Recruiter Quick Actions
Save time matching credentials, copying profile links, or grabbing contact records.
Interactive Stack Verification
Select a skill below or search to verify production experience, scale metrics, and view related technical notes.
Next.js & React
Production frontend framework for high-traffic commerce and dashboard platforms.
- Spearheaded Nykaa's SuperStore UI revamp with modern layouts, optimized hydration, and modular code.
- Achieved 95%+ unit-test coverage on critical checkout and catalog pages using Jest and React Testing Library.
- Configured static site generation (SSG) and incremental static regeneration (ISR) to reduce TTFB to under 80ms.
Supporting Proof of Work (Tech Notes)
Selected work
Selected work
Engineering case studies first — GenAI, voice agents, and high-traffic platforms. Earlier client sites live under Work filters.
Featured case studyAI Platform Engineering
Agent Evaluation & Voice-UI Sync
Case study: Designing a voice-first agent (Gemini Live) with real-time UI screen synchronization, prompt versioning, and a unified agent evaluation framework.
AI Engineering · Voice Systems
Voice Agent Guardrails & Observability
Case study: Architecting an auditable voice agent for tele-calling with multi-layer guardrails, secure tool execution, and OTel tracing.
AI Engineering · System Design
B2B Retail GenAI Assistant
Case study: GenAI shopping assistant for a B2B retail platform—LangGraph, JSON embeddings for RAG without a vector DB, built for commerce scale.
E-Commerce Platform
Gram Bahar
Gram Bahar: E-commerce hub with customer-friendly site & admin panel for seamless product management, orders, payments, and tracking.
Experience
Where I've shipped
Five years across high-traffic commerce, SaaS, and applied AI — each role with measurable outcomes, not just responsibilities.
Software Engineer - II · Nykaa E-Retail Limited
January 2026 – Present
Bengaluru, Karnataka, India · Onsite
Shipped three production AI features: a GenAI chatbot (JSON embeddings, 40% accuracy gain, 95% test coverage), an auditable voice bot (PyCAT, LangGraph, OTel tracing, multi-layer guardrails, safe tool execution), and a voice-first orchestrator (Gemini Live) syncing screen UI via WebSockets.
Senior Full-stack Developer · Kaamwork Technologies Private Limited
October 2024 – December 2025
Bengaluru, Karnataka, India · Onsite
Improved system efficiency by ~18% by building Next.js and Nest.js applications with PostgreSQL and Prisma through optimized API endpoints.
Senior Front-end Web Developer · Services & Consulting Force SRL
February 2021 – October 2024
Rome, Italy · Remote
Reached ~99.9% uptime for 500k+ daily users via a Next.js and Hugo hybrid front-end with Node.js.
Writing & code
Deep-dives and open source
How I think about engineering — architecture write-ups, tech notes, and public code.
Stateful Agent Orchestration with LangGraph
Design deterministic, cycle-safe multi-agent systems using LangGraph state machines with explicit transition states, guardrails, and runtime validation.
Hybrid Retrieval and Cross-Encoder Reranking for RAG
How to combine BM25 keyword search with dense vector embeddings and cross-encoder reranking for reliable production RAG systems.
Type-Safe LLM Outputs with Zod and JSON Schema
Bypass fragile prompt engineering with runtime-checked, schema-constrained LLM outputs in production TypeScript pipelines.
Tools
Browser utilities
Small tools I built for everyday tasks. Everything runs client-side.
FAQ
Frequently asked
Quick answers for recruiters, founders, and anyone evaluating a collaboration.
What is your current role?
I'm a Software Engineer II at Nykaa in Bangalore, working on B2B commerce engineering and Generative AI—including a production LangGraph chatbot (JSON embeddings), an auditable voice bot with guardrails and OpenTelemetry tracing, and a unified agent evaluation platform. SE-II is a senior IC band at Nykaa scale; before that I spent 3.7 years at Services & Consulting Force.
What do you build?
Full-stack web applications and AI/LLM products end to end—React/Next.js frontends, Node.js/Nest.js backends, RAG systems, and voice-first agents with dynamic UI screen sync—with performance, observability, and safety built-in.
What roles are you looking for?
Full-stack or AI engineering roles on product and platform teams — realistically the L4 / SDE II / E4 band, with room to grow. Bangalore-based; open to remote, hybrid, or in-office. Fastest path — book 15 minutes on Cal.com, or reach me via the contact page, email, or WhatsApp.
What technologies do you specialize in?
TypeScript, Next.js, React, Node.js/Nest.js, Go, Generative AI / LLM / RAG with LangGraph, PostgreSQL, REST APIs and microservices, Docker, Kubernetes, and AWS — with a strong focus on system design, testing, and web performance.
Hiring for full-stack or AI engineering?
Open to product and platform roles at the mid/senior IC band. Book a 15-minute intro, or send a note — I usually reply within a day.