Senior AI Engineer
Summary
Senior AI Engineer at Bayer building a production full-stack AI application: a Python/FastAPI backend that orchestrates multiple LLM providers (LiteLLM, LangChain/LangGraph, MCP) plus a TypeScript/React/Next.js frontend, deployed on Alibaba Cloud Kubernetes with PostgreSQL/Redis/Qdrant, GitHub Actions CI/CD, and a full observability stack.
YOU TASKS AND RESPONSIBILITES
- Design and develop backend services using Python, integrating multiple LLM providers via LiteLLM routing
- Build and maintain the frontend application using TypeScript, React 19, and Next.js 16 with Mantine UI components and Tailwind CSS
- Implement and extend LLM agent orchestration using LangChain/LangGraph, including stateful agent workflows, tool calling, and middleware pipelines
- Develop and maintain MCP server/client integrations for extensible tool ecosystems
- Design and optimize database schemas and queries across PostgreSQL, Redis, and Qdrant
- Manage cloud infrastructure on Alibaba Cloud
- Build and maintain CI/CD pipelines using GitHub Actions, including Docker image builds, automated testing, and multi-environment deployments
- Manage Kubernetes workloads including Helm charts, autoscaling, CronJobs, and sandboxing
- Implement and maintain observability stack: Langfuse, Prometheus, Grafana dashboards, and error tracking
- Integrate AI capabilities into production workflows: RAG pipelines, document parsing, voice agents, code sandboxing, and research tools
- Implement background job processing with Redis Queue and design scalable async architectures
- Ensure production reliability through proper monitoring, alerting, and incident response
- Maintain comprehensive API documentation and follow API versioning best practices
- Communicate effectively in English (spoken and written) with international cross-functional teams on a daily basis
- Participate in code reviews, architectural discussions, and technical decision-making
- Document architectural decisions and maintain knowledge-sharing resources
WHO YOU ARE
- Excellent English oral and written communication skills — daily collaboration with international teams requires fluent spoken English
- Strong Python development experience — FastAPI, async programming, SQLAlchemy/SQLModel, Pydantic, and production-grade API development
- Experience with LLM application development — LangChain, LangGraph, or similar LLM orchestration frameworks; prompt engineering; RAG pipelines; multi-provider LLM integration
- Frontend development with TypeScript and React — Next.js, state management, component libraries, and Tailwind CSS
- Infrastructure as Code experience — Terraform, managing cloud resources declaratively
- Kubernetes and container orchestration — deploying and managing workloads on managed Kubernetes, Helm charts, autoscaling
- Cloud platform experience — Alibaba Cloud or AWS; services including managed databases, object storage, container registries, load balancers, and secrets management
- Database proficiency — PostgreSQL, Redis, and vector databases
- CI/CD pipeline development — GitHub Actions or similar; Docker multi-stage builds; automated testing and deployment workflows
- Observability and monitoring — experience with distributed tracing, metrics collection, log aggregation, and error tracking
- Strong problem-solving skills with a focus on building reliable, scalable production systems
- Bachelor's degree or above in Computer Science, Software Engineering, or related field; or equivalent practical experience (5+ years)
- Experience with MCP or similar tool-calling protocols
- Experience with real-time communication
- Experience with document processing pipelines
- Familiarity with feature flag systems
- Experience with load testing and property-based testing
- Knowledge of security practices: sandboxing, OAuth/OIDC, KMS encryption
隐私保护提示:拜耳深知个人信息对您而言十分重要,并严格遵守法律法规,竭力保证您的个人信息安全。如果您投递简历,您的简历及其他您主动提供的个人信息将被录入拜耳招聘系统,敬请知悉。
Skills
- AI
- API
- Api Documentation
- AWS
- CI/CD
- Cloud
- CSS
- Docker
- FastAPI
- GitHub
- GitHub Actions
- Grafana
- Helm
- Infrastructure as Code
- Kubernetes
- LangChain
- Langfuse
- LangGraph
- LLM
- MCP
- Next.js
- OAuth
- Observability
- OpenID
- PostgreSQL
- Prometheus
- Prompt Engineering
- Pydantic
- Python
- Qdrant
- RAG
- React
- Redis
- Secrets Management
- SQLAlchemy
- Tailwind
- Terraform
- Test Automation
- TypeScript
- Vector Databases
