Python Developer – Agentic AI / LLM / RAG Engineer
-
Infosys Limited
- Bangalore
- 2 - 5 Years
- Full Time
- AgentOps
- chains
- LLMOps
- Python
- Responsible AI
Posted September 17, 2026 applications close October 17, 2026
Please sign in or register for free to apply.
Job Description
Responsibilities
Key Responsibilities
Develop and maintain AI applications using Python.
Design and implement Agentic AI systems using frameworks such as LangChain, LangGraph, CrewAI, AutoGen, or similar.
Build and optimize RAG pipelines using vector databases and retrieval frameworks.
Integrate and fine-tune Large Language Models (LLMs) including OpenAI, Azure OpenAI, Llama, Claude, Gemini, or similar.
Develop APIs and microservices for AI applications.
Implement prompt engineering, workflow orchestration, and AI agent collaboration patterns.
Create scalable solutions using cloud platforms such as Azure, AWS, or GCP.
Monitor, evaluate, and improve AI model performance, accuracy, and response quality.
Collaborate with business and technology teams to translate requirements into AI-driven solutions.
Additional Responsibilities
Technology Stack
Technology | Artificial Intelligence & Automation
Skill Category | Python Development, Agentic AI, LLM, RAG, Generative AI
Primary Skills | Python, LangChain, LangGraph, CrewAI, Azure OpenAI, RAG, Vector Databases
Secondary Skills | FastAPI, Docker, Kubernetes, Azure AI Search, MLOps
Technical and Professional Requirements
Required Skills
Strong programming experience in Python.
Hands-on experience with LLMs, Generative AI, Agentic AI, and RAG architectures.
Experience with LangChain, LangGraph, CrewAI, AutoGen, LlamaIndex, or equivalent frameworks.
Knowledge of vector databases such as Pinecone, ChromaDB, Weaviate, FAISS, or Azure AI Search.
Experience with REST APIs, FastAPI, Flask, or Django.
Understanding of embeddings, semantic search, prompt engineering, and model evaluation.
Experience with Git, CI/CD, and software development best practices.
Knowledge of cloud AI services (Azure OpenAI preferred).
Preferred Skills
Experience with multi-agent architectures and AI orchestration.
Knowledge of MLOps, model deployment, and containerization (Docker/Kubernetes).
Exposure to NLP, machine learning, and deep learning concepts.
Experience with enterprise AI governance, security, and responsible AI practices.
Preferred Skills
- AgentOps
- LLMOps
- chains
- Responsible AI
- Python
Educational Requirements
Bachelor of Engineering