Future - Staff Applied AI Engineer

Aimlroles; San Francisco (CA); Remote; USD 250,000 - 300,000; Full time

Job summary

Future (future.co) is building the AI foundation for a Health Coach product. We offer fully remote work across US time zones with optional weeks at Brentwood LA HQ. Base salary is $250K–$300K with competitive equity; visa not supported for this role.

Join a strong team to ship production LLM agents, develop tools, and optimize latency, cost, and reliability while collaborating with experts in health coaching and AI.

Qualifications

• 4–10 years; shipped LLM agents to production.
• Strong big-tech background, ideally moved to startups or founded a company.
• Proficient in Python/async, LangChain/LangGraph, Pydantic, Langfuse, AWS/Bedrock.
• US citizen or Green Card holder; comfortable in a beta-stage environment.

Responsibilities

• Build and ship production AI agents for Health Coach: tool-calling LLMs, structured output, parallel API orchestration, streaming
• AI features: coach matching, clinical-leaning guidance (sleep, nutrition, fitness), human in the loop
• Own the loop: prototype, Langfuse evals/rubrics, deploy, monitor traces, iterate
• Improve reliability/latency/cost: prompt caching, token budgets, retries, observability
• Write agent tools (Pydantic-validated integrations) in an EPD pod

Skills

Python

Async Python

LangChain

LangGraph

Pydantic

Langfuse

AWS Bedrock

Production LLM agents

Tools

AWS

Bedrock

Terraform

CDK

Job description

Future (future.co): personal fitness/health coaching; building the AI foundation of a new Health Coach product. $110M raised; board includes Tom Brady, Eddie Cue, Adam Bain.

Comp: $250K-$300K base (SF rates for all US) + competitive equity. Location: Fully remote, US time zones; optional anchor weeks at Brentwood LA HQ. Visa: Not open to visas (US citizen / Green Card).

Responsibilities

• Build and ship production AI agents for Health Coach: tool-calling LLMs, structured output, parallel API orchestration, streaming

• AI features: coach matching, clinical-leaning guidance (sleep, nutrition, fitness), human in the loop

• Own the loop: prototype, Langfuse evals/rubrics, deploy, monitor traces, iterate

• Improve reliability/latency/cost: prompt caching, token budgets, retries, observability

• Write agent tools (Pydantic-validated integrations) in an EPD pod

Tech stack: Python, Async Python, LangChain, LangGraph, LLMs, Pydantic, JSON Schema, SSE, Webhooks, Langfuse, AWS, AWS Bedrock, OpenTelemetry, Datadog, Terraform, CDK

Source: https://www.paraform.com/share/future/cmur5lxlk000g06nis011p9o1

• 4-10 yrs; shipped LLM agents to production

• Strong big-tech background, ideally moved to startups or founded a company

• Python/async, LangChain/LangGraph, Pydantic, Langfuse, AWS/Bedrock

• Independent in a beta-stage environment; US citizen/GC