[Remote] Senior Applied AI Engineer

Note: The job is a remote job and is open to candidates in USA. Function Health is the AI operating system for health, aiming to empower individuals to live healthier lives through proactive, data-driven insights. They are seeking a Senior Applied AI Engineer to architect and build agent workflows that leverage health data, ensuring reliable and actionable recommendations for members.ResponsibilitiesArchitect and build stateful, graph-based agent workflows with tool use, planning, and memoryIntegrate LLMs and multimodal models via structured I/O (JSON Schema, Pydantic validators) and function/tool callingBuild high-reliability APIs and streaming services for real-time inference, speech, and visionOwn production readiness: tracing, logging, metrics, rate limiting, circuit breakers, and SLOsStand up eval pipelines: offline golden sets, LLM-as-judge with human rubrics, online A/B, and regression tests in CIImplement retrieval and memory: hybrid search, vector and graph retrieval, semantic caches, and long-horizon contextOptimize cost/latency: model routing, prompt and tool selection, quantization, and KV cache/prefill strategiesPartner cross-functionally to translate research into robust production systems and iterate quickly behind evaluation gatesMentor engineers through design docs and architecture decisionsSkills1+ years building agentic AI systems; 6+ years as a full-stack or ML engineer, building production backends or ML systems in Python, Go, or similarFluency with agentic orchestration (e.g., LangGraph, PydanticAI, DSPy, LlamaIndex) and tool/function callingExperience integrating frontier LLMs and multimodal models via managed APIs or self-hosted servingStrong with API design and backend frameworks (FastAPI, Flask) and event-driven architecturesData systems expertise with PostgreSQL, including token streaming and throughput tuningRetrieval and memory: vector databases (pgvector, Pinecone, Weaviate, Milvus), hybrid search, and graph/knowledge storageProduction evals: LLM-as-judge, human-in-the-loop, rubric design, and CI-integrated regression testsObservability and SRE: OpenTelemetry traces, metrics, structured logs, SLOs, dashboards, and on-call triageCloud-native delivery: Kubernetes, Terraform, Docker, GPU scheduling/autoscaling on AWS or GCPCI/CD proficiency with GitHub Actions and test automation for prompts, tools, and agentsClear, concise communication and high ownership in fast-paced environmentsReal-time multimodal systems: streaming ASR, low-latency TTS, WebRTC, and vision pipelinesRAG expertise beyond basics: Graph RAG, multi-hop retrieval, sub-agents, query planning, and freshness policiesSafety and governance: policy-as-code, red-teaming, PII handling, audit logs, and role-based tool authorizationRegulated data experience (HIPAA, SOC 2, GDPR) and data residency controlsPersonalization at inference time, long-term memory agents, session state, and episodic memory storesExperience with consumer-scale AI apps, high-traffic systems, or on-device/edge acceleration (WebGPU)BenefitsCompetitive salary and benefits packageFlexible working hoursA dynamic work environment where creativity and innovation are encouragedCompany OverviewFunction Health is a health platform offering lab tests to help individuals monitor their health. It was founded in 2022, and is headquartered in Austin, Texas, USA, with a workforce of 11-50 employees. Its website is https://www.functionhealth.com.