Senior Software Development Engineer II - Agentic AI & LLM platforms (#26-074)

Strategic Analysis, Inc. (SA) Is seeking a **Software Engineer** to support the Agentic AI \& LLM platform at Advanced Research Projects Agency for Health (ARPA\-H) **Overview:** The GRACE team at ARPA\-H is building the next generation of agentic AI to transform how the agency accelerates research, makes decisions, and ships products at scale. GRACE is ARPA\-H's production AI assistant, and we are evolving it into an ecosystem of autonomous, multi\-agent systems. The team is a small, startup\-minded team that ships fast and owns what they build end\-to\-end. They are looking for an SDE II who is hungry to contribute to a real production system, not a sandbox. The best person for this role communicates clearly, collaborates without ego, and brings genuine empathy for the users whose work they are making better. The person is a self\-starter with a high bar and a high sense of urgency. He or She plays well with others and makes the people around him or her better. **Roles and Responsibilities:** \- Build Agentic AI Systems \- Build LLM\-Powered Features \- Own the Backend \- Contribute to Infrastructure **Requirements:** \- 3\+ years of professional software engineering experience building and operating production systems \- Proven experience in high\-velocity environments where you contributed to shipping real products end\-to\-end \- Strong proficiency in Python and at least one other backend language; familiarity with modern backend frameworks and async patterns \- Solid understanding of algorithms, data structures, distributed systems, and software design patterns \- Experience building and operating systems on major cloud platforms (AWS, GCP, or Azure) \- Experience with containerization (Docker) and working within CI/CD pipelines \- Clear, direct communicator who gives and receives feedback well, works with empathy, and makes the people around them better \- Self\-starter with a high bar and high sense of urgency; you do not wait to be told what to do next **Preferred Qualifications:** \- Hands\-on experience building features on top of LLMs in production: tool\-calling, RAG, multi\-step reasoning, and context management \- Familiarity with A2A (Agent\-to\-Agent) communication patterns and multi\-agent orchestration frameworks \- Familiarity with MCP at the client/consumer layer: how agents discover and invoke tools via MCP \- Working knowledge of prompt engineering and LLM behavior across model families; you understand why Claude and GPT respond differently to the same prompt \- Experience with LLM evaluation, grounding assessment, or regression testing for AI\-powered systems \- Awareness of token economics at the application layer: cost\-per\-query, context budget management, and prompt efficiency \- Experience on Microsoft Azure: Azure Functions, API Management, Container Apps, or Azure OpenAI Service \- Familiarity with secrets management, least\-privilege access, and security\-conscious engineering practices \- Experience in startup or early\-stage environments: comfort with ambiguity, rapid iteration, and wearing multiple hats \- Experience in healthcare, life sciences, or other regulated domains is a plus but not required Education: Bachelor's or Master's degree in Computer Science, Software Engineering, or a related field, or equivalent practical experience Location: Remote with occasional travel Clearance: Ability to obtain HHS Public Trust.