AI Engineer, Agentic Systems

Company Overview

Function was founded with a singular focus: empower you to live 100 healthy years. We’re doing that by using the best available technology to make sure people don't suffer or die a preventable death. Function has been recognized as one of Fast Company’s Most Innovative Companies of 2024, and is venture‑backed by Andreessen Horowitz (a16z). Hundreds of thousands of members have joined Function to take control of their health.

We are growing our team and seeking out world‑class talent that deeply believes in our mission to positively impact global health, has a relentless bias toward action and a growth mindset. Function fosters a collaborative and dynamic environment, where every day we are building the future.

You will design, ship, and scale production‑grade, stateful multi‑agent systems end to end—spanning orchestration graphs, model serving, real‑time inference, and observability. You’ll partner with product, infra, and research to integrate LLMs and multimodal models (voice, vision, structured data) into consumer and internal workflows with strong safety, reliability, and cost controls. This is a hands‑on role for a high‑ownership engineer with deep systems expertise and a track record of delivering AI agents at scale.

• Ship agentic features that move core product KPIs with measurable quality and latency targets.
• Establish evaluation gates and on‑call reliability for AI systems that handle real users and revenue.
• Reduce cost‑to‑serve via model routing, KV cache reuse, and retrieval quality improvements.

• 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.
• Lead cloud‑native deployments on Kubernetes with GPU autoscaling, canary/shadow releases, and feature flags.
• Partner cross‑functionally to translate research into robust production systems and iterate quickly behind evaluation gates.
• Mentor engineers through code reviews, design docs, and architecture decisions.

• 2.5+ 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., Lang Graph, Pydantic
  
  AI, DSPy, Llama Index) and tool/function calling.
• Experience integrating frontier LLMs and multimodal models via managed APIs or self‑hosted serving.
• Deep understanding of model serving and inference optimization (vLLM/Triton/TGI/SGLang, batching, KV cache reuse).
• Strong with API design and backend frameworks (FastAPI, Flask) and event‑driven architectures.
• Data systems expertise with Postgre
  
  SQL and Redis, including caching, 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:
  Open Telemetry 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 Git Hub Actions and test automation for prompts, tools, and agents.
• Clear, concise communication and high ownership in fast‑paced environments.

• Real‑time multimodal systems: streaming ASR, low‑latency TTS, WebRTC, and vision pipelines.
• Post‑training/fine‑tuning: DPO/ORPO, RLHF, preference data generation, and safety alignment.
• RAG…