About this role.
Future is seeking a product-focused Applied AI Engineer to build, evaluate, deploy, and operate LLM-powered agent capabilities for its personalized health platform. The role covers the full production lifecycle, including rapid prototyping, evaluation harnesses, staging and production deployment, tracing, and iterative reliability improvements. Core technical work includes Python services, tool-calling LLMs, structured outputs, async APIs, streaming responses, Pydantic validation, and cloud infrastructure. Success requires balancing model quality, safety, personalization, latency, reliability, and operating cost while collaborating closely with product, mobile, and backend teams.
Role DNA
A quick view of the complexity, pace, ownership and collaboration implied by the job description.
Job Complexity
5/5Pace & Pressure
5/5Autonomy Level
5/5Communication Load
4/5Salary analysis
Estimated compensation compared with the broader US market for similar roles.
Core skills
Skills and capabilities most closely associated with this opportunity.
Sample interview questions
I would explain the user problem, agent architecture, tools and guardrails, then describe building an evaluation dataset with representative and edge-case requests. I would cover offline quality metrics, safety checks, latency and cost thresholds, staged rollout, production tracing, and the feedback loop used to improve the agent after launch.
I would define strict Pydantic or JSON Schema contracts for every tool input and output, validate user intent before execution, and use idempotency keys for submissions. I would add bounded retries, timeouts, clear error states, authorization checks, audit logs, and a fallback path when the model produces invalid or incomplete arguments.
I would create a curated evaluation set segmented by goals, experience levels, constraints, and high-risk edge cases. Rubrics would assess factual grounding, appropriate uncertainty, adherence to product safety policy, personalization quality, and actionability, combining automated checks, LLM-as-a-judge calibration, and periodic expert human review.
I would inspect traces to isolate time spent in retrieval, model calls, tool calls, serialization, and retries. Likely improvements include prompt caching, context pruning and summarization, smaller models for routing or extraction, parallelizing independent API calls, tighter token budgets, and better tool-selection logic.
I would start with a shared definition of the user outcome, constraints, and measurable success criteria. I would document API contracts, interaction states, model limitations, safety behavior, telemetry requirements, and rollout plans, then use regular reviews and production data to align teams on iterations.
About Us:
Future is building a personalized guidance system for lifelong health. We help people understand what to do next for their body, goals, and stage of life — then support them in turning those decisions into sustained behavior change. By combining AI, human expertise, personal health data, and accountability, Future helps members improve performance today while building the resilience, capacity, and healthspan they need for decades to come.
About the Role
We’re looking for an Applied AI Engineer to help us build and ship AI-powered features that directly improve our product experience and business outcomes. This is a hands-on, product-focused role where you’ll take ideas from concept to production — designing intelligent systems, validating them with real users, and turning them into reliable, scalable services.
You’ll work at the intersection of AI, product, and engineering — partnering closely with cross-functional teams to identify high-impact opportunities, prototype quickly, and iterate based on data. This isn’t a research-only role. You’ll own the full lifecycle: experimentation, evaluation, deployment, monitoring, and continuous improvement.
The ideal candidate is excited about applying LLMs and modern ML tooling to real-world problems. You think in terms of systems, tradeoffs, and outcomes — not just models. You care about performance, quality, latency, and cost in production. Most importantly, you’re motivated by shipping impactful AI experiences that customers actually use.
What You’ll Do
- Build and ship AI agents that serve real users: tool-calling LLM systems with structured output, parallel API orchestration, and streaming responses.
- Design evaluation harnesses and quality scoring — we use Langfuse, rubrics to measure safety, effectiveness, and personalization.
- Own the full loop: prototype a new agent capability, validate it with evals, deploy it 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.
What You Bring
- 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: 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).
Compensation & Benefits
We believe great people should be well paid and meaningfully invested in what they’re building.
Base Salary $ 215,000– $ 250,000/ year + equity. The salary range is set based on multiple considerations including business needs, market demands, talent availability, experience, and unique skills and attributes. The base pay range is subject to change and may be modified in the future.
Equity Equity participation offered alongside base compensation.
Health Coverage Comprehensive medical, vision, dental, and disability insurance plus tax savings accounts for all eligible employees.
Retirement 401(k) plan with tax-advantaged savings options.
Remote-First Employment eligible to all employees located anywhere in the continental US. No travel required.
Wellness & Development Monthly health and fitness stipend contributing to overall wellbeing, access to a mental health platform, reimbursement for medical travel, and an annual learning & development stipend.
Flexible Time Off Flexible PTO so you can rest, recharge, and take care of life outside of work.
Future Membership Enjoy our platform for free!
Life at Future
Equity: Meaningful equity package.
Health Coverage: All employees who meet eligibility requirements receive comprehensive medical, dental, vision, and disability insurance, plus tax-advantaged savings accounts.
Retirement: 401(k) plan.
Wellness: Monthly wellness stipend for fitness, recovery, and overall wellbeing, plus access to mental health resources and therapy support.
Flexible Time Off: Flexible PTO so you can rest, recharge, and take care of life outside of work.
Learning & Development: Annual budget for courses, conferences, coaching, and tools that help you grow in your craft.
Future Membership: Enjoy our platform for free.
Equal Employment Opportunities at Future
We are committed to building a future where every member of our community, is healthy, cared for, and advancing forward together. Future is an equal opportunity employer. We do not discriminate based on gender, ethnicity, sexual orientation, religion, age, civil or family status, disability or race.
Upload your resume now
- To unlock remote work opportunities and be discovered by global employers.
This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content.
