Senior AI Engineer

Bayer Consumer Health is undertaking an ambitious AI initiative to build intelligent, production-grade AI solutions that make enterprise data and documents accessible, queryable, and actionable across commercial, marketing, product supply, and R&D domains globally.

• Strong Python engineering with production-grade Generative AI system experience.
• Hands-on experience with LangGraph and/or LangChain for multi-agent and agentic AI systems.
• Experience building RAG pipelines over structured and unstructured data (e.g., LightRAG).
• Solid understanding and practical experience with Text-to-SQL solutions.
• Strong API development and integration skills (e.g., FastAPI).
• Proficiency with Azure cloud services (Azure Apps, Containers, Storage) and/or AWS equivalents.
• Experience with relational and vector databases (PostgreSQL, pgvector, MS SQL) and Docker containerization.
• Business-oriented mindset with ability to communicate effectively with non-technical stakeholders.
• Strong problem-solving skills and pragmatic, production-first engineering mindset.
• 5+ years of experience in AI Engineering, Software Engineering, or Machine Learning Engineering.
• Fluent in English, both written and spoken.

Nice to have:

• Experience with document parsing and unstructured-to-structured data extraction pipelines.
• Hands-on experience with Databricks: Unity Catalogue, Genie Spaces, and Agent Bricks.
• Experience with LLM context and prompt engineering.
• Experience with AI observability, evaluation frameworks, and automated testing (e.g., Langfuse).
• Knowledge of Model Context Protocol for tool integration.
• Understanding of CI/CD principles, GitHub Actions, and Infrastructure as Code (Terraform, ARM Templates).
• Understanding of semantic layer and data management concepts for enterprise data.

The Agentic AI Builder:

• Design and implement multi-agent AI systems in Python using LangGraph and LangChain.
• Build composable, plug-and-play agent architectures that evolve with LLM capabilities and business needs.

The Document Intelligence Engineer:

• Build AI pipelines to parse PDFs, Word documents, images, and mixed-format files.
• Extract, normalize, and validate structured information at scale using OCR, document layout models, and LLM-powered extraction chains.

The RAG Architect:

• Design and implement Retrieval-Augmented Generation pipelines over unstructured document corpora and structured metadata.
• Apply dynamic filtering and re-ranking to maintain accuracy without exceeding token budgets.

The Text-to-SQL Specialist:

• Build conversational data interfaces converting natural language to SQL.
• Handle ambiguous questions, multi-turn conversations, schema linking, self-correction loops, and context injection.

The Evaluator:

• Build automated regression testing frameworks.
• Support A/B testing of LLM configurations and integrate human feedback loops for continuous quality improvement.

The Business Partner:

• Engage with stakeholders across commercial, marketing, product supply, and R&D to understand problems before coding.
• Translate real business challenges into well-scoped AI use cases ensuring measurable business impact.