Senior AI Engineer

 

At Bayer we’re visionaries, driven to solve the world’s toughest challenges and striving for a world where ,Health for all, Hunger for none’ is no longer a dream, but a real possibility. We’re doing it with energy, curiosity and sheer dedication, always learning from unique perspectives of those around us, expanding our thinking, growing our capabilities and redefining ‘impossible’. There are so many reasons to join us. If you’re hungry to build a varied and meaningful career in a community of brilliant and diverse minds to make a real difference, there’s only one choice.

 

Senior AI Engineer 

 

Role Summary 

 

In Digital Workplace, we are seeking a Backend Engineer with NLP specialization to join our User Support team’s agentic transformation. This role is critical to building the Agentic Content Management System (ACMS) — a modular, headless, AI-driven content management platform designed for ingesting, validating, structuring, and publishing enterprise knowledge. 

 

Unlike a chatbot or single-channel solution, ACMS enables a system of agents that collaboratively create, enrich, and manage content, then deliver it across multiple channels — voice, mobile, chat, conversational interfaces, articles, and knowledge bases — serving users, human agents, and digital agents alike. 

 

The engineer will start by delivering the Enhanced Article Co-Creation Agent, the first agent in a multi-agent system for complete knowledge article lifecycle management. It drafts first versions of knowledge content based on themes generated by the Signal Agent and performs four roles in one:  

 

1.                  Writer — produces plain-language, user-centric articles.  

2.                  Intent Structurer — breaks articles into machine-readable intents (e.g., goal, object, action).  

3.                  Format Converter — structures output for AI and omnichannel use (JSON, Markdown, HTML).  

4.                  Self-contained Module — optimized for agent consumption and reuse across platforms.  

 

Beyond this initial project, the role will contribute to designing and scaling additional agentic microservices across the ACMS ecosystem.

 

Key Accountabilities 

 

·                Microservices & APIs: Design, build, and operate production-grade microservices (FastAPI preferred or Node.js) with versioned REST contracts; uphold API-first, headless patterns for multi-channel delivery.  

·                NLP/LLM Integration: Implement pipelines for text generation, intent/metadata extraction, chunking & embeddings; integrate vector search as needed (e.g., pgvector/Qdrant/Pinecone).  

·                Data & Storage: Model and maintain Postgres schemas (articles, intents); manage migrations, performance, and data quality.  

·                Packaging & Ops: Ship Dockerized services with configuration, observability (logging/metrics/tracing), runbooks, and basic SLOs; collaborate with the hub for Kubernetes deployments.  

·                Security & Messaging: Implement OAuth2/OIDC, secure service-to-service communication, and leverage message brokers where appropriate.  

·                Pipelines & Streaming: Contribute to real-time and batch ingestion (e.g., Kafka, Airflow) and/or cloud-native functions (AWS Lambda, Azure Functions, GCP Functions).  

·                Agentic Planning: Where beneficial, apply AI planning/decision methods such as Markov Decision Processes (MDP) or Monte Carlo Tree Search (MCTS) to improve reliability and autonomy.  

·                Collaboration: Partner with product owner, platform, data, and security teams on requirements, reviews, and releases aligned to enterprise standards.  

 

Required Qualifications & Experience 

 

Backend Engineering  

·                Python (FastAPI) or Node.js; strong REST API design; Docker and containerization.  

·                Relational DB design (Postgres or equivalent); schema modeling, migrations, and query tuning.  

 

NLP / AI  

·                Integrating LLMs (Azure OpenAI/OpenAI/Hugging Face, etc.).  

·                Chunking, embeddings, intent extraction; familiarity with vector databases.  

 

Enterprise Practices