I am
Aditya Dey.
Backend developer with 2.5+ years building and shipping production APIs, RAG systems, and document-processing pipelines. Comfortable owning the whole path — from a FastAPI service to a Dockerized deploy on a plain server or AWS. Applied GenAI and AI/ML where it earns its place, and casual frontend when the job needs it.
ToolsoftheTrade
Technologies I use to build fast, reliable, and scalable systems.
click a node to expand its branch
tap a category to expand it
// languages
WorkHistory
Dec 2023 – Present
Full-timeBackend Developer - AI
Workmates Core2Cloud
Own backend architecture end-to-end for AI-driven products — designing REST APIs and microservices, modelling data across relational and vector stores, and taking features from design through deployment and monitoring. Integrate LLM providers and retrieval pipelines into production systems, build and maintain agentic workflows, and keep an eye on latency, cost, and reliability once things ship. Lead GenAI initiatives on the team, review code, and mentor junior engineers.
Aug – Oct 2023
InternshipML Engineer Intern
Prodigy Infotech
Built ML models for NLP and recommendation systems using scikit-learn and PyTorch. Contributed to production pipelines and improved user experience through data-driven feature work.
WhatIBuild
Backend engineering, deployment, and applied AI — built and shipped end to end.
Backend & APIs
Production FastAPI services, event-driven microservices with Kafka, and scalable Python backends built to ship.
Deployment & Cloud
Ship the whole app — Dockerized or on a plain server. AWS (ECS), CI/CD pipelines, and IaC with Terraform.
Databases & Retrieval
Relational and vector data — PostgreSQL/pgvector, MongoDB, Qdrant — with hybrid search and low-latency retrieval.
Applied Gen AI
GenAI wired into real services: LangGraph agents, RAG pipelines, and tool-use chatbots — practical, not research.
MLOps & LLMOps
Model and prompt lifecycle — monitoring, evaluation, versioning, observability, and automated deploy pipelines.
ML Engineering
Train, evaluate, and ship ML models for NLP, classification, and recommendation — from notebook to API.
HowIWork
Understand
I start by deeply understanding the goal and the problem space before writing a line of code.
Prototype
I build quick prototypes to test assumptions and gather early feedback fast.
Iterate
I refine the solution based on real-world usage, performance metrics, and edge cases.
Deliver
I ship clean, documented, production-ready code with proper testing and observability.
Let's ship something.
Have a backend to build, an app to deploy, or an idea to prototype? Let's talk.