SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 215,000 - 250,000 / annual
Future is building a personalized guidance system for lifelong health, combining AI, human expertise, personal health data, and accountability to help members improve performance and build long-term resilience.
You'll join as an Applied AI Engineer in a hands-on, product-focused role where you'll take AI-powered features from concept to production. This is not a research-only position—you'll own the full lifecycle: experimentation, evaluation, deployment, monitoring, and continuous improvement.
Key responsibilities:
- Build and ship AI agents serving real users: tool-calling LLM systems with structured output, parallel API orchestration, and streaming responses
- Design evaluation harnesses and quality scoring using tools like Langfuse and rubrics to measure safety, effectiveness, and personalization
- Own the complete loop: prototype new agent capabilities, validate with evals, deploy to staging and production, monitor traces, and iterate
- Improve reliability, latency, and cost through prompt caching strategies, token budgets, retry logic, and observability
- Write the tools agents use: API integrations with Pydantic validation, exercise search over local databases, structured workout submission
- Partner closely with cross-functional teams (product, mobile, backend engineers) to identify high-impact opportunities and prototype quickly
You'll work at the intersection of AI, product, and engineering, thinking in terms of systems, tradeoffs, and outcomes—not just models. You care about performance, quality, latency, and cost in production, and you're motivated by shipping impactful AI experiences that customers actually use.
Requirements:
- Strong Python skills: you've built and deployed services on large production systems
- Experience with LangChain/LangGraph or similar agent frameworks
- Hands-on experience with LLMs in production: prompt engineering, tool/function calling, structured output, evaluation
- Comfort with async Python, HTTP APIs, and streaming protocols (SSE, webhooks)
- Experience with data validation and schema design (Pydantic, JSON Schema)
- Ability to debug across layers: from a broken LLM tool call to a misconfigured Terraform resource
- Clear communication skills; you'll work directly with product, mobile, and backend engineers
Nice to have:
- Familiarity with AWS (Bedrock, ECR, CloudFront, S3, Cognito) or other cloud agent hosting
- Observability and tracing tools (Langfuse, OpenTelemetry, Datadog)
- Exposure to evaluation frameworks: LLM-as-a-judge, automated scoring, dataset management
- Infrastructure-as-code (Terraform, CDK)
