We are looking for an AI Engineer to design, build, and evolve intelligent agents in an AWS cloud environment, leveraging Gemini models and agentic AI architectures. This role works closely with data, product, and engineering teams to deliver scalable AI solutions applied to retail, operations, and customer experience.
Key responsibilities
• Design, develop, and maintain LLM-based intelligent agents (Agentic AI)
• Build inference pipelines and agent orchestration on AWS
• Integrate Gemini models with cloud services and internal applications
• Implement Retrieval-Augmented Generation (RAG) using structured and unstructured data
• Ensure observability, performance, security, and governance of AI solutions
• Collaborate with product teams to define use cases and success metrics
• Automate testing, versioning, and deployment of AI systems
• Contribute to MLOps and LLMOps best practices
Must-have:
• Solid experience as an AI Engineer, Machine Learning Engineer, or similar role
• Hands-on experience with LLMs and agent architectures (multi-agent systems, tool calling, planners, memory)
• Experience with Gemini (Google) or equivalent models (Open AI, Anthropic, etc.)
• Strong AWS experience (Lambda, ECS/EKS, S3, Dynamo DB, API Gateway, IAM, Cloud Watch)
• Strong Python development skills (async programming, APIs, AI frameworks)
• Experience with LLM and agent frameworks (Lang Chain, Lang Graph, Llama Index, or similar)
• Experience with RAG, embeddings, and vector databases
• Familiarity with CI/CD pipelines, infrastructure as code, and automation
• Understanding of security, privacy, and data governance in AI solutions