Senior Applied AI Engineer

Role Description

We sit on something rare: a fast-growing longitudinal health dataset spanning 50M+ lab tests, 160+ biomarkers per member, advanced imaging, and wearable signals, captured continuously rather than once a year at a checkup.

You'll own the agentic system that turns a member's health data into clear next steps, working alongside their clinicians. Day to day, that means building and operating production multi-agent systems end to end:

• Orchestration graphs
• Tool use and memory
• Retrieval over a member's records
• Evals and observability to keep it reliable

You'll wire frontier LLMs into Function's proprietary data, and hold the whole thing to the safety, latency, and cost controls healthcare demands.

This is a hands-on, high-ownership role for an engineer who has built agents at scale and wants their work measured in healthy years of human life, not just benchmarks.

Impact You'll Drive

• Put a concierge doctor in every member's pocket: an agent that reasons over a lifetime of labs, imaging, and wearable signals and tells them what to do next.
• Turn our longitudinal health dataset into decisions, not dashboards, so members act on their health rather than just view it.
• Make health AI that people trust with their lives: every recommendation earns its way past evaluation gates and clinician review before it reaches a member.
• Catch what a once-a-year physical misses, surfacing the early signal across 160+ biomarkers before it becomes a diagnosis.

Key Responsibilities

• Architect and build stateful, graph-based agent workflows with tool use, planning, and memory.
• Integrate LLMs and multimodal models via structured I/O (JSON Schema, Pydantic validators) and function/tool calling.
• Build high-reliability APIs and streaming services for real-time inference, speech, and vision.
• Own production readiness: tracing, logging, metrics, rate limiting, circuit breakers, and SLOs.
• Stand up eval pipelines: offline golden sets, LLM-as-judge with human rubrics, online A/B, and regression tests in CI.
• Implement retrieval and memory: hybrid search, vector and graph retrieval, semantic caches, and long-horizon context.
• Optimize cost/latency: model routing, prompt and tool selection, quantization, and KV cache/prefill strategies.
• Partner cross-functionally to translate research into robust production systems and iterate quickly behind evaluation gates.
• Mentor engineers through design docs and architecture decisions.

Qualifications

• 1+ years building agentic AI systems; 6+ years as a full-stack or ML engineer, building production backends or ML systems in Python, Go, or similar.
• Fluency with agentic orchestration (e.g., LangGraph, PydanticAI, DSPy, LlamaIndex) and tool/function calling.
• Experience integrating frontier LLMs and multimodal models via managed APIs or self-hosted serving.
• Strong with API design and backend frameworks (FastAPI, Flask) and event-driven architectures.
• Data systems expertise with PostgreSQL, including token streaming and throughput tuning.
• Retrieval and memory: vector databases (pgvector, Pinecone, Weaviate, Milvus), hybrid search, and graph/knowledge storage.
• Production evals: LLM-as-judge, human-in-the-loop, rubric design, and CI-integrated regression tests.
• Observability and SRE: OpenTelemetry traces, metrics, structured logs, SLOs, dashboards, and on-call triage.
• Cloud-native delivery: Kubernetes, Terraform, Docker, GPU scheduling/autoscaling on AWS or GCP.
• CI/CD proficiency with GitHub Actions and test automation for prompts, tools, and agents.
• Clear, concise communication and high ownership in fast-paced environments.

Nice to Haves

• Real-time multimodal systems: streaming ASR, low-latency TTS, WebRTC, and vision pipelines.
• RAG expertise beyond basics: Graph RAG, multi-hop retrieval, sub-agents, query planning, and freshness policies.
• Safety and governance: policy-as-code, red-teaming, PII handling, audit logs, and role-based tool authorization.
• Regulated data experience (HIPAA, SOC 2, GDPR) and data residency controls.
• Personalization at inference time, long-term memory agents, session state, and episodic memory stores.
• Experience with consumer-scale AI apps, high-traffic systems, or on-device/edge acceleration (WebGPU).

Why You'll Love Working With Us

• We value our team at Function and offer a competitive salary and benefits package.
• Flexible working hours and a dynamic work environment where creativity and innovation are encouraged.
• If you are a highly motivated and experienced individual who is passionate about using technology to improve people’s lives, we would love to hear from you.