• Strong experience with Python for backend and AI development. 

• Hands-on experience with FastAPI (or similar Python web frameworks). 

• Practical experience with LLM frameworks such as:  

• OpenAI Agents SDK 

• LangChain 

• Or equivalent agent orchestration frameworks 

• Solid understanding of prompt engineering techniques. 

• Experience with memory management and context strategies for GenAI applications. 

• Experience deploying applications to Azure Cloud. 

• Familiarity with Docker and containerized deployments. 

• Experience using GitHub for version control and CI/CD pipelines. 

• Ability to work closely with product teams and adapt to evolving requirements. 

Key Responsibilities 

• Design, develop, and enhance Generative AI solutions integrated into our product ecosystem. 

• Translate product and business requirements into robust GenAI features. 

• Build and maintain backend services using FastAPI and Python. 

• Develop and integrate LLM-powered agents using frameworks such as OpenAI Agents SDK, LangChain, or similar. 

• Implement effective prompt engineering strategies, including prompt optimization and evaluation. 

• Design and manage conversation memory and context handling for multi-turn and agent-based systems. 

• Deploy and operate GenAI services in Azure Cloud environments. 

• Containerize applications using Docker and contribute to scalable deployment architectures. 

• Collaborate with product managers, engineers, and stakeholders to iteratively improve AI-driven features. 

• Maintain high code quality through version control, testing, and CI/CD pipelines (GitHub). 

• Monitor, troubleshoot, and optimize performance, cost, and reliability of GenAI solutions.