Engineering Intelligence

Aditya Dey

I am a

"I engineer AI systems from model to production — multi-agent workflows, RAG pipelines, voice interfaces, ML training, and the MLOps infrastructure that keeps them running reliably at scale."

0+ yr

Experience

Projects Built

Tech Domains

Let's Talk

Resume

Kolkata, IN

Live · Open-Meteo

Explore

Tech Stack

ToolsoftheTrade

Technologies I use to build fast, reliable, and scalable systems.

Gen AI & Agents

LangGraph

LangChain

RAG Pipelines

AWS Bedrock

Google Vertex AI

Groq

Crew AI

Embeddings

expertproficientfamiliar

ML & MLOps / LLMOps

PyTorch

scikit-learn

Hugging Face

MLflow

DVC

LangSmith

Airflow

Prometheus

Grafana

LiveKit

n8n

Strands SDK

expertproficientfamiliar

Backend & APIs

Python

FastAPI

Flask

C++

Kafka

REST APIs

Microservices

Pydantic

expertproficientfamiliar

Cloud & DevOps

AWS (ECS, Lambda, S3, Bedrock)

Docker

Kubernetes

Terraform

GitHub Actions

Git

expertproficientfamiliar

Databases & Vectors

PostgreSQL

MongoDB

Qdrant

Redis

MySQL

OpenSearch

expertproficientfamiliar

Right Now

WhatI'mUpTo

A live snapshot — updated as things change. Last updated: March 2026

In Progress

Currently Building

Voice-RAG & Fraud Detection

Production-grade AI systems — a modular voice assistant with RAG on AWS Bedrock, and a real-time event-driven fraud detection pipeline with Kafka and ML inference.

Ongoing

Currently Learning

LLMOps & MLOps

Kubernetes

MLflow

DVC

Apache Airflow

AWS SageMaker

Prometheus

Grafana

Jenkins CI/CD

LLM Deployment

Specialisations

WhatIBuild

End-to-end AI engineering — from model experimentation to production deployment.

Gen AI & Agentic Systems

Multi-agent LangGraph workflows, RAG pipelines, tool-use agents, and context-aware chatbots for production environments.

LangGraph

LangChain

RAG

Crew AI

Bedrock

Voice AI & Real-time

End-to-end voice AI pipelines with LiveKit, real-time STT/TTS, and streaming multimodal interfaces.

LiveKit

Bedrock

Whisper

Streaming

FastAPI

ML Engineering

Train, evaluate, and ship ML models for NLP, classification, and recommendation — from notebook to API.

PyTorch

scikit-learn

Hugging Face

Feature Eng

MLOps & LLMOps

Full model lifecycle management — monitoring, evaluation, versioning, observability, and automated deployment pipelines.

LangSmith

MLflow

n8n

GitHub Actions

Strands

Backend & APIs

Production-grade FastAPI services, event-driven microservices with Kafka, and scalable Python backends.

FastAPI

Kafka

Microservices

Python

Pydantic

Cloud & Deployment

AWS infrastructure, containerised deployments on ECS, CI/CD pipelines, and IaC with Terraform.

AWS

Docker

Terraform

ECS

GitHub Actions

Workflow

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 Build Something Great

I'm open to backend, cloud, and AI/ML engineering roles. Have a project in mind? Let's talk.

Get in Touch Download CV