About
Full-stack Software Engineer with 2 years of hands-on experience building AI-powered backend systems and production-grade infrastructure. Specialises in LLM integration pipelines, intelligent document processing, Kubernetes orchestration, and multi-agent AI architectures. Currently driving end-to-end AI automation at a product startup — from raw OCR extraction to structured data delivery — while owning DevOps, backend, and AI system design
Skills
Programming Languages:
Backend:
Frontend:
AI / ML:
Database:
DevOps & Cloud:
Work Experience
- •Architected an end-to-end AI document processing pipeline that ingests invoices from email, runs OCR, and extracts structured fields via LLM - replacing manual data entry and exporting clean output to Excel for downstream finance workflows.
- •Built a multi-LLM provider orchestrator routing requests across OpenAI, Anthropic, and other vendors based on cost, latency, and task-type conditions - enabling model switching without vendor lock-in.
- •Designed an AI-driven candidate proctoring system that conducts LLM-generated interviews, evaluates responses in real time across multiple dimensions (technical depth, communication, problem-solving), and produces structured assessment reports.
- •Led the full migration from Docker Compose to Kubernetes, implementing Helm charts, HPA, and liveness/readiness probes - improving deployment reliability, scalability, and operational observability.
- •Implemented shared NFS storage across multiple Kubernetes pods for concurrent access to large document workloads without data duplication, supporting high-throughput async processing pipelines.
- •Developed a multi-agent orchestrator for an AI app-builder platform where specialised agents dynamically hand off tasks (planning, code generation, validation, deployment) based on context.
Education
Check out my latest work
I've worked on a variety of projects, from simple websites to complex web applications. Here are a few of my favorites.
Audinexa (AI Audio Generation Platform)
- •
Developed an AI-driven Text-to-Speech SaaS platform for generating, managing, and playing high-quality audio.
- •
Built a custom Chatterbox TTS backend with voice cloning using FastAPI, for fast generation.
- •
Integrated AWS S3 for secure audio storage, NextAuth for authentication, and Polar.sh for billing.
- •
Designed a scalable full-stack architecture using Next.js, TRPC, Prisma, and PostgreSQL.
Study Notion (Ed-Tech)
- •
Developed a full-stack EdTech platform enabling instructors to create and manage courses with role-based access.
- •
Integrated video streaming, progress tracking, and cloud storage for seamless learning experiences.
- •
Built secure payment workflows using Razorpay with dynamic coupon support and order history.
- •
Implemented REST APIs, authentication middleware, and a modular architecture for scalability and maintainability.
Mystery Message (Anonymous Messaging Application)
- •
Built a web app using Next.js for creating and decoding anonymous mystery messages.
- •
Implemented secure backend APIs with Next.js API routes and MongoDB for message storage.
- •
Designed a clean and responsive UI with TailwindCSS for smooth user experience.
- •
Focused on privacy and anonymity, ensuring safe one-time message sharing.