Role Overview

Build and deploy production Generative AI, LLM, and agentic applications on Python and FastAPI backends.

Key Responsibilities

- Design, build, and deploy Generative AI, LLM, and agentic AI applications into production.

- Build scalable Python and FastAPI backend services, REST APIs, and microservices for AI applications.

- Develop RAG solutions using LangChain or LlamaIndex with vector databases (Pinecone, ChromaDB, FAISS, Weaviate).

- Design and optimize prompts using zero-shot, few-shot, chain-of-thought, and function calling techniques.

- Integrate with cloud AI platforms (AWS Bedrock, SageMaker, Azure OpenAI, or Vertex AI), following Git, CI/CD, and documentation standards.

Must Have Skills

- 5 - 8 years of software development,



including 2+ years in GenAI / LLM application development and 1+ year in agentic AI.

- Robust Python with FastAPI in production applications.

- Hands-on Generative AI, LLM, and agentic AI work delivered in live production projects.

- Advanced prompt engineering, including function calling.

- Able to walk through your implementation, architecture, use cases, and business outcomes in the interview.

Nice to Have

- TypeScript

- LangChain or LlamaIndex

- Vector databases (Pinecone, ChromaDB, FAISS, Weaviate)

- AWS Bedrock, SageMaker, Azure OpenAI, or Google Vertex AI

- GraphQL, NLP, embeddings, and transformer models

📌 AI/ML Developer (Generative AI & Agentic AI) (Chennai)
🏢 Tenth Planet Technologies
📍 Chennai