Experience:

• 1 to 3 years of substantive, hands-on agentic work experience

Responsibilities:

• Design and build AI agents and agentic workflows including tool-use, function calling, multi-step task orchestration, and agent loops
• Integrate LLM APIs into .NET application code with authentication, streaming, error handling, and cost/latency tradeoffs
• Deliver AI features end-to-end from backend integration to production-ready front-end
• Build custom agents and tools with Claude Agent SDK and wire agent loops
• Author custom skills and slash commands for Claude Code to codify workflows
• Implement RAG pipelines and integrate vector stores to ground agent outputs in trusted data
• Instrument agents for evaluation and observability to verify, measure, and audit outputs
• Apply AI-specific risk controls for regulated clinical environments addressing hallucination, determinism, and auditability
• Use Claude Code or equivalent agentic CLI daily as a primary development tool

Additional responsibilities:

• Work at the intersection of science, technology, and patient experience to deliver digital solutions
• Collaborate with teams across clinical, technology, data, and operations
• Contribute to advancing clinical research and bringing new treatments to patients faster

Nice to have:

• Claude Agent SDK experience building custom agents and wiring agent loops
• Knowledge of agent primitives such as hooks, skills, subagents, and session/state management
• Experience authoring custom skills or slash commands for Claude Code
• Exposure to Model Context Protocol (MCP) for connecting agents to internal tools and data sources
• Working knowledge of RAG patterns and vector store integration
• Awareness of AI-specific risk areas relevant to regulated environments including OWASP LLM Top 10

More skills:

.NET development, C#, Core, Full-stack development, AI agents and agentic workflows, LLM API integration (Anthropic, OpenAI, Bedrock, Azure OpenAI), Vector stores (Qdrant, pgvector, Pinecone), Evaluation and observability of AI outputs

Other:

• Global environment with opportunities for career growth and innovation
• Collaborative teams combining science, technology, and operational expertise
• Equal opportunity workplace and affirmative action employer
• Background check and identity verification required prior to start