Software Engineer - AI Accelerated Development

About Signant Health At Signant Health, we help bring life-changing treatments to patients faster. We are a global evidence generation company that supports clinical trials with smart technology, scientific expertise, and hands-on operational support — so better data leads to better decisions in healthcare. We embrace AI and advanced technologies to enhance every aspect of what we do, from data analysis to operational efficiency.

Our teams work at the intersection of science, technology, and patient experience, delivering digital solutions powered by AI innovation that make clinical trials more efficient, more accurate, and more accessible around the world. Trusted by leading pharmaceutical companies and CROs, our platforms and services support studies across more than 90 countries and have contributed to hundreds of new drug approvals.

If you are motivated by meaningful work, global impact, and innovation in clinical research and digital health — including the opportunity to work with cutting-edge AI technologies — you will find purpose and opportunity at Signant Health.

About The Role Signant Health is looking for a Software Engineer – AI Accelerated Development to build AI-powered, agentic features into our clinical trial platforms. Working across the .NET stack, you will take AI capabilities from backend LLM integration through to a usable front-end — designing agents and agentic workflows, not just prompting a model. This is a hands-on engineering role for someone who works with agentic tooling every day and wants to ship production AI in a regulated, high-impact environment. We weigh the depth of your AI and agentic build experience more heavily than years of general experience: a developer with one to three years of substantive, hands-on agentic work is exactly the profile we are targeting.

KEY ACCOUNTABILITIES – Function

• 1-5 Years of experience in AI, .NET and Fullstack.
• Design and build AI agents and agentic workflows — tool-use/function calling, multi-step task orchestration, and agent loops — that power Signant Health’s clinical trial platforms.
• Integrate LLM APIs (Anthropic, OpenAI, Bedrock, or Azure OpenAI) into .NET application code, handling authentication, streaming, error handling, and cost/latency tradeoffs.
• Deliver AI features end-to-end, taking them from backend integration through to a usable, production-ready front-end.
• Build custom agents and tools with the Claude Agent SDK, wiring and steering agent loops.
• Author custom skills and slash commands for Claude Code to codify team-specific workflows.
• Implement RAG pipelines and integrate vector stores (e.g. Qdrant, pgvector, Pinecone) to ground agent outputs in trusted data.
• Instrument agents for evaluation and observability so their outputs can be verified, measured, and audited.
• Apply AI-specific risk controls appropriate to a regulated clinical environment, addressing hallucination, determinism, and auditability of agent decisions.
• Use Claude Code (or an equivalent agentic CLI) daily as a primary development tool, reviewing and steering AI-generated diffs.

Knowledge, Skills & Attributes Essential

• Full-stack .NET development — C#/ASP.NET Core on the backend paired with a modern front-end framework.
• Hands-on agentic development experience — building AI agents or agentic workflows (tool-use/function calling, multi-step task orchestration, agent loops); not just prompting an LLM, but building systems around one.
• Practical LLM API integration (Anthropic, OpenAI, Bedrock, or Azure OpenAI), including authentication, streaming, error handling, and cost/latency tradeoffs.
• Proven full-stack delivery of AI features — able to take an agentic/AI feature from backend integration through to a usable front-end, not just a notebook prototype.
• Daily, hands-on use of Claude Code (or an equivalent agentic CLI) as a primary development tool — comfortable working through multi-step agentic sessions and reviewing and steering AI-generated diffs, rather than occasional autocomplete-style use.
• Prompt engineering — designing and iterating on system prompts as production software contracts, not one-off experiments.
• Python proficiency as the preferred language for AI/agent tooling; comfort with async patterns a plus.
• Evaluation and observability literacy — able to reason about whether an agent’s output is correct and instrument it to prove so.

Desirable:

• Claude Agent SDK experienc…