Senior AI Engineer @ Bayer

Master’s degree (or equivalent) in Computer Science, Data/AI, Mathematics, or a related field; PhD is an advantage. 5+ years of professional experience in AI/software/ML engineering, with end-to-end product delivery in production environments. Advanced Python and production-grade API development (REST/gRPC), authN/authZ (OAuth2/OIDC), rate limiting. Containerization (Docker) expertise; Kubernetes experience is a plus. Proficiency in AWS and/or Azure: AWS (examples): Lambda, ECS/Fargate/EKS, API Gateway, S3, RDS, Secrets Manager, Bedrock. Azure (examples): Functions, AKS, API Management, Storage, PostgreSQL/Cosmos DB, Key Vault, Azure OpenAI. Strong CI/CD knowledge, especially GitHub Actions. Infrastructure as Code (Terraform preferred) Solid grasp of LLMs and embeddings: context management, tool calling, streaming, and latency/cost trade-offs. Monitoring and traceability mindset: OpenTelemetry, Langfuse/LangSmith. Strong software engineering fundamentals: testing, code reviews, error handling, reliability/resilience. Excellent problem-solving and communication skills; fluent in English (written & spoken). Preferred: Hands-on with agent frameworks (e.g. LangChain, LangGraph, PydanticAI) as well as FastAPI and FastMCP for MCP server development. Preferred: RAG and vector search proficiency (pgvector, OpenSearch) Preferred: Experience with relational databases (e.g., PostgreSQL); Databricks experience a plus. Join us to shape how AI scales at Bayer. We are hiring a Senior AI Engineer for the Machine Learning and Artificial Intelligence unit within Bayer’s Enterprise Data & Analytics Platform. You will design and ship global, production-grade AI solutions for Finance, Supply Chain, HR, Procurement, Legal, and Communications- owning delivery end-to-end from PoC to secure, observable, and scalable services in the cloud. Our international team across Poland, Germany, Spain, and India works with LLMs and embeddings, classic ML, and optimization on a modern, cloud-native stack (Python, AWS/Azure, Databricks). If building robust APIs, MCP servers, and agentic systems with strong monitoring and traceability excites you, this is the place to build at scale. ,[Industrialize and scale successful GenAI prototypes into secure, resilient IT products for Enabling Functions., Design, implement, and operate cloud-native APIs and microservices for AI workloads using Python and FastAPI, following schema-first design (OpenAPI/gRPC)., Develop Model Context Protocol (MCP) servers (FastMCP) to safely expose enterprise tools and data to agents, ensuring robust permissions and auditing., Architect agent workflows with LangChain, LangGraph, and PydanticAI (tool calling, memory, event-driven orchestration)., Build reliable text-to-sql solutions and/or RAG services with high-quality embeddings, indexing, reranking, and caching for performance and cost efficiency., Implement CI/CD pipelines (GitHub Actions) with automated testing., Deploy on AWS and/or Azure (containers, serverless, API gateways, managed databases, object storage, secrets)., Ensure end-to-end observability: structured prompt/response logging with redaction, token/latency/cost tracking, OpenTelemetry tracing, and model/agent monitoring (e.g., Langfuse/LangSmith/MLflow)., Establish safety and quality controls: evaluation pipelines, prompt/chain regression tests, content guardrails, and injection defenses., Collaborate across Data Science, MLOps/DevOps, Architecture, Product, and Business to align solutions with outcomes; contribute to stack decisions and cost/scalability trade-offs., Promote continuous learning via code reviews, tech talks, and mentoring on AI engineering best practices.] Requirements: Python, AWS Additionally: Sport subscription, Private healthcare, Canteen, Modern office.