Description
Job Summary

Key Responsibilities

- Build AI-powered applications using OpenAI, Claude, Gemini, Llama, and Hugging Face models

- Develop RAG pipelines using LlamaIndex and LangChain

- Implement prompt engineering, embeddings, semantic search, and vector retrieval

- Build APIs and microservices using FastAPI and Python

- Integrate AI solutions with enterprise applications and workflows

- Evaluate and optimize model accuracy, latency, and reliability

- Develop monitoring, logging, and evaluation frameworks for AI applications

- Support deployment and production operations of AI workloads

Required Skills Mandatory

- 3+ years of Python development experience

- Experience with OpenAI, Claude, Gemini, or Hugging Face

- Experience with LangChain or LlamaIndex

- Experience with Vector Databases and Embeddings





- Experience building APIs using FastAPI

- Understanding of RAG architectures

- Docker and Cloud deployment experience

- Solid prompt engineering skills

Preferred

- LangGraph

- Agentic AI concepts

- Fine-tuning and PEFT techniques

- AWS, Azure, or GCP

- LangSmith / LangWatch

- MLflow or experiment tracking

Interview Focus Areas

Candidates should be able to explain:

- AI applications delivered

- RAG architecture used

- Embedding and retrieval strategy

- Prompt optimization techniques

- Production deployment approach

- Monitoring and evaluation mechanisms

- Business challenges solved using GenAI

📌 AI QA Engineer - Bangalore, IND (India)
🏢 Important Group
📍 India