AI/LLM Engineer - Data Modeling

Description :

We are hiring an AI / LLM Engineer with strong Python skills to build Generative AI and LLM-powered applications. This role focuses on RAG pipelines, OpenAI/LLaMA integration, and AI product development.

Key Responsibilities :

- Build LLM-powered applications

- Implement RAG (Retrieval-Augmented Generation) pipelines

- Integrate OpenAI API / LLaMA API

- Develop AI apps using Streamlit

- Monitor LLM performance using LangFuse

- Track system health using Datadog

- Deploy AI solutions on AWS / LocalStack

- Optimize prompt engineering and model performance

Required Skills :

- Python

- LLMs / Generative AI

- RAG

- OpenAI API / LLaMA API

- Streamlit

- LangFuse / LangChain (preferred)

- AWS / Cloud basics

Nice to Have :

- Vector Databases (Pinecone, FAISS, Weaviate)

- AI evaluation frameworks

- AI monitoring / MLOps

Ideal Candidate : Someone who has built real GenAI products, not just experiments -experience with production LLM apps is a big plus.