Senior Software Engineer, Agentic AI

Cadence Health

13h•Remote

About The Position

Cadence is seeking a Senior Software Engineer to design and ship production agents that synthesize real-time clinical data, surface proactive care recommendations, and take action on behalf of clinicians. This role involves taking agent architectures from prototype to production in a domain where reliability directly affects patient outcomes. The engineer will own the full lifecycle of AI-powered clinical workflows, including retrieval, reasoning, tool use, evaluation, and safety guardrails. The company is focused on re-architecting U.S. healthcare by building a remote care delivery platform that helps patients stay healthy, out of the hospital, and at home. Cadence's AI-powered platform supports tens of thousands of patients nationwide, enabling proactive, population-level care, with a future vision of intelligent systems helping clinicians identify risk earlier, guide interventions, and reduce operational burdens.

Requirements

Bachelor's or Master’s degree in Computer Science, Engineering or related field, or equivalent work experience
5+ years of software engineering experience, with 2+ years building AI/ML-powered systems in production
Hands-on experience with LLM APIs (OpenAI, Anthropic, open-source models) including prompt engineering, tool use / function calling, and structured outputs
Experience building RAG systems: embeddings, vector stores, retrieval optimization, and grounding
Experience in a high-growth, fast-paced environment with end-to-end ownership from design through production

Nice To Haves

Experience with agent frameworks or orchestration patterns (tool calling, planners, multi-agent coordination)
Fine-tuning experience (SFT, RLHF, LoRA) on domain-specific tasks
Healthcare or regulated-industry experience (HIPAA, SOC 2, clinical data handling)

Responsibilities

Design, build, and deploy clinical AI agents that reason over patient context, invoke tools, and generate care recommendations.
Own reliability, observability, and cost efficiency of LLM-powered workflows at scale.
Build and optimize RAG pipelines over clinical knowledge bases, treatment protocols, and real-time patient data.
Develop evaluation frameworks: offline benchmarks, safety tests, regression suites, and LLM-as-judge pipelines wired into CI/CD.
Design multi-step agent orchestration: planning, memory, tool use, error recovery, and human-in-the-loop escalation paths.
Collaborate with clinical, product, and engineering teams to translate patient care needs into AI system design.
Stay at the forefront of AI and engineering best practices, continuously pushing the team to raise the bar on quality, performance, and architecture.