Join a global organization from the life sciences sector and help shape a next-generation platform for building, deploying, and governing AI-powered agents at enterprise scale. You will play a key role in defining architecture standards and technical direction for a production-grade AI agent platform operating in a highly regulated environment.
Key responsibilities
- Define the target architecture and technical standards for AI agents across the platform.
- Design single-agent and multi-agent systems, orchestration patterns, RAG solutions, and memory management.
- Establish best practices covering the entire agent lifecycle, including development, testing, deployment, and monitoring.
- Define security, governance, access control, and multi-tenant isolation standards.
- Support engineering teams with complex agentic use cases and architectural decisions.
Requirements
- Proven experience designing and delivering production-grade AI, GenAI, or LLM-based solutions.
- Strong software engineering background with proficiency in Python, APIs, and distributed systems.
- Experience with agent frameworks such as LangGraph, LangChain, Langflow, or similar.
- Deep understanding of LLM integration, prompt engineering, tool calling, and context management.
- Hands-on experience with RAG architectures, vector search, and knowledge retrieval strategies.
- Strong cloud architecture experience, ideally within AWS environments.
What we offer
- Ongoing support from a dedicated agent ensuring project continuity and professional development.
- Access to a comprehensive learning and development platform with webinars and industry reports.
- A complete benefits package including medical care, life insurance, and sports cards.
- Opportunities to share knowledge and collaborate with experienced IT experts.