Aditya Dey in nature
About Me

Hey, I'm Aditya

Kolkata, India

I'm from Kolkata — a city that's loud, layered, and genuinely beautiful if you know where to look. That's where I picked up a camera and started chasing light.

Photography is the thing I keep coming back to. There's something about being patient enough for the right moment — whether it's golden hour in the Himalayas or rain bouncing off a street at 6am — that I find genuinely calming. I shoot with my phone mostly, which forces you to make interesting decisions instead of hiding behind gear.

During the day I build AI systems — agents, pipelines, voice interfaces, the kind of software that's meant to reason, not just execute. But I'm just as likely to be out with a camera as I am debugging a LangGraph workflow.

I also hike when I can, game casually, and have a soft spot for anywhere with mountains and a decent viewpoint.

Photography

chasing light & landscapes

Hiking

mountains & quiet viewpoints

Gaming

casual, nothing competitive

Building AI

agents, RAG, voice systems

I shoot with my phone.

No DSLR, no mirrorless. Shooting on a phone forces you to think about composition, timing, and light instead of relying on equipment. Most of my best frames came from being in the right place at the right time — mountains, rivers, early mornings.

@PIXFACTS
Experience

Work History

01

Dec 2023 – Present

Full-time

Backend Developer - AI

Workmates Core2Cloud

Building production AI systems at scale — 2M+ document intelligence pipeline with AWS Textract & Qdrant RAG, multi-template invoice extraction with Bedrock LLM normalisation, sub-100ms policy recommendation via pgvector hybrid search, WhatsApp NBFC loan advisory chatbot, and an autonomous CloudWatch incident-response agent with LangGraph. Leads GenAI development and mentors junior engineers.

LangGraphRAGAWS BedrockFastAPILangSmith
02

Aug – Oct 2023

Internship

ML 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.

PyTorchscikit-learnNLPPython
Skills

Technical Proficiency

Gen AI & Agents

LangGraph
LangChain
RAG Pipelines
AWS Bedrock
Google Vertex AI
Groq
Crew AI
Embeddings
MCP

ML & MLOps / LLMOps

PyTorch
scikit-learn
Hugging Face
MLflow
DVC
LangSmith
Airflow
Prometheus
Grafana
LiveKit
n8n
Strands SDK

Backend & APIs

Python
FastAPI
Flask
C++
Kafka
REST APIs
Microservices
Pydantic

Cloud & DevOps

AWS (ECS, Bedrock, SageMaker, Textract)
Docker
Kubernetes
Terraform
GitHub Actions
Git

Databases & Vectors

PostgreSQL
MongoDB
Qdrant
Redis
MySQL
OpenSearch
ChromaDB
Activity

GitHub Contributions

AditHash

adeywm