Planned hiring
AI Engineer
Lucy is a proactive AI coach from Lucy Labs that lives on your desktop as a cloud-backed app.
Planned hiring. This description explains the work we are preparing to hire for; it is not a confirmed start date or offer.
Turn evaluated AI methods into controlled software that can help Lucy interpret work and deliver useful coaching. You will build the runtime that connects models, context, knowledge and product behavior, making quality, uncertainty, latency and cost visible enough to guide engineering decisions.
Your mission
Turn evaluated AI methods into controlled software that can help Lucy interpret work and deliver useful coaching. You will build the runtime that connects models, context, knowledge and product behavior, making quality, uncertainty, latency and cost visible enough to guide engineering decisions.
What you will build
- Implement versioned inference and extraction services for Behavior, Coaching and public-source knowledge ingestion. Preserve source references, confidence, abstention and structured outputs across service boundaries instead of treating every generated answer as a valid fact.
- Build model and provider routing with explicit eligibility by data class, purpose and processing location. Implement the permitted processing route and its verified protections; external AI and cloud services can be part of that route. A fallback must preserve the purpose, permission and control boundary.
- Assemble authorized context from Behavior, Analytics and Knowledge through defined interfaces. Carry customer tool restrictions into recommendation behavior and keep customer-private material isolated from reusable public knowledge.
- Implement runtime checks, timeouts, bounded retries, safe failure responses and rollback. Track model, prompt and configuration versions so a regression can be reproduced and reversed without guessing which combination produced it.
- Integrate independent evaluation suites into release workflows and compare quality, latency, cost and failure behavior on the same versioned candidate. Instrument runtime behavior without exposing private prompts or Content in diagnostic traces.
- Productionize methods developed with Applied Science and behavioral specialists. Start with the narrowest evaluated approach that serves the agreed use case, and document limitations that Product and the user experience must communicate.
Your partners and boundaries
Applied Science owns inference and recommendation methods; the Evaluation engineer independently designs datasets, adjudication and quality evidence. You own serving and integration, not independent approval of your own scientific claims. Product Engineering and Desktop deliver the experience, while Platform/SRE own shared infrastructure and reliability. Lucy coaches people to build solutions; this role does not authorize autonomous action in customer systems. The family combines AI runtime and AI platform/MLOps duties without adding a separate team for each tool.
What you bring
You have delivered AI integrations or ML systems with strong software practices: typed interfaces, versioning, tests, observability and recoverable releases. You can explain model-serving or API tradeoffs using evidence, identify leakage and unreliable outputs, and distinguish runtime correctness from model quality. Familiarity with structured extraction and retrieval is useful. We value careful review of AI-generated code and the ability to communicate uncertain results as clearly as successful ones.
Your first 90 days
Agree a bounded inference path and its acceptance evidence with Product, Science and Evaluation. Build a versioned runtime with traceable outputs and permitted-data routing. Demonstrate timeout handling, evaluation execution and rollback before a pilot release decision. Produce an initial quality/latency/cost comparison and document unresolved failure modes so the team can choose its next improvement deliberately.
Next step
Express your interest
Email people@lucylabs.ai with the role title, a short introduction and relevant CV or portfolio. This is planned hiring; we will confirm current availability and the individual working arrangement.
Lucy Labs confirms the working arrangement, employer, location, eligibility, compensation and terms for each role. Our mailing address does not determine the job location or guarantee remote employment, worldwide eligibility or visa sponsorship.
Do not send passwords, government identifiers or bank details. Read the application privacy notice.
Frequently asked questions
Is this role open at Lucy Labs?
Lucy Labs lists this role as planned hiring. Availability depends on the need, team readiness and individual arrangement; it does not promise an immediate vacancy or start date.
Where does this work take place at Lucy Labs?
Lucy Labs confirms the working arrangement, employer, location, eligibility, compensation and terms for each role. Our mailing address does not determine the job location or guarantee remote employment, worldwide eligibility or visa sponsorship.
What does this role own at Lucy Labs?
Lucy Labs: Turn evaluated AI methods into controlled software that can help Lucy interpret work and deliver useful coaching. You will build the runtime that connects models, context, knowledge and product behavior, making quality, uncertainty, latency and cost visible enough to guide engineering decisions.
How do I express interest in Lucy Labs?
Email people@lucylabs.ai with the role title, a short introduction and relevant CV or portfolio. Lucy Labs uses the application to assess and respond to it; retention for future opportunities is a separate explained purpose and choice.
