AI Engineer – Generative AI, Python, FastAPI, LLM

About the role

We are looking for an AI Engineer specialized in generative AI to join our product team in Hyderabad. You will design, develop and integrate large‑language‑model (LLM) based features that enhance our applications.

Key responsibilities

• Design and implement generative AI solutions within the product ecosystem.
• Translate business requirements into robust LLM‑powered features.
• Build and maintain backend services using Python and FastAPI.
• Develop agents with OpenAI Agents SDK, LangChain or similar frameworks.
• Apply prompt‑engineering techniques, optimise prompts and evaluate performance.
• Manage conversation memory and context for multi‑turn interactions.
• Deploy, monitor and operate services on Azure Cloud, using Docker containers.
• Maintain code quality with GitHub version control, testing and CI/CD pipelines.
• Collaborate with product managers, engineers and stakeholders to continuously improve AI‑driven functionality.

Required profile

• Strong experience in Python for backend and AI development.
• Hands‑on experience with FastAPI or comparable Python web frameworks.
• Practical knowledge of LLM orchestration tools such as OpenAI Agents SDK or LangChain.
• Solid understanding of prompt engineering and context management for generative AI.
• Experience deploying applications to Azure Cloud and using Docker.
• Familiarity with GitHub, version control and CI/CD pipelines.

Required skills

• Python
• FastAPI
• OpenAI Agents SDK
• LangChain
• Prompt engineering
• Azure Cloud
• Docker
• GitHub
• CI/CD pipelines