• 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: o OpenAI Agents SDK o LangChain o 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.