Lucy Labs
Talk to Lucy
Open role

AI Platform / MLOps Engineer

This role helps build Lucy, the proactive AI coach from Lucy Labs that lives on your desktop as a cloud-backed app, while the product is in development with design partners.

Owns model routing, versioning, eval execution and AI observability.

Apply for this role All roles
Planned work

About the role

At Lucy Labs, this role owns the purpose described below.

The AI Platform / MLOps Engineer owns the platform layer for model routing, prompt and model versioning, eval execution, AI observability, local/cloud routing, cost controls, and safety-layer integration.

This role turns AI experiments into governed product infrastructure. It is distinct from generic DevOps and distinct from behavior-inference modeling.

The mission

At Lucy Labs, this role's mission is defined by the outcome and work below.

Build AI platform systems that:

  • Route model and prompt calls reliably across local and cloud providers
  • Version prompts, models, evals, datasets, and safety policies
  • Measure quality, latency, cost, and failure modes for AI-assisted features
  • Support local-first and privacy-sensitive inference paths
  • Let engineering move fast without losing model accountability

What you'd own

At Lucy Labs, this role turns its mission into concrete responsibilities in each area.

1. Model Routing and Runtime Platform

For 1. Model Routing and Runtime Platform, Lucy Labs expects this role to own the responsibilities below.

  • Build model/provider routing and fallback systems
  • Support local/cloud routing decisions tied to privacy, cost, latency, and quality
  • Implement model invocation APIs, context assembly boundaries, and safety checks
  • Integrate with backend, desktop, behavior inference, and coaching systems

2. Prompt, Model, and Eval Versioning

For 2. Prompt, Model, and Eval Versioning, Lucy Labs expects this role to own the responsibilities below.

  • Build versioned prompt and model configuration management
  • Connect model/prompt changes to eval suites and release gates
  • Track which model/prompt/version produced each derived output
  • Support rollback and A/B testing for AI behavior

3. AI Observability and Cost Control

For 3. AI Observability and Cost Control, Lucy Labs expects this role to own the responsibilities below.

  • Monitor latency, token/cost, error classes, hallucination/failure modes, and safety interventions
  • Build dashboards for model health and feature-level AI cost
  • Implement budgets, throttles, caching, and graceful degradation
  • Partner with Finance/BizOps on cost model assumptions where needed

4. Platform Partnership

For 4. Platform Partnership, Lucy Labs expects this role to own the responsibilities below.

  • Work with Data/Evaluation on automated eval execution and regression reporting
  • Work with Privacy/Trust on policy-aware routing and logging boundaries
  • Work with Applied Behavior Inference on model migration and confidence semantics
  • Work with DevOps/SRE on production reliability and incident response

What success looks like

Lucy Labs defines these milestones as role outcomes, not metrics for measuring the person.

60 days
Model routing, prompt versioning, and AI observability plan are in place
90 days
First eval-gated AI feature can be versioned, measured, and rolled back
6 months
AI platform supports multiple product pipelines with cost and quality controls
12 months
AI runtime is reliable enough for enterprise design partners and local/cloud routing

Experience and fit

Lucy Labs looks for the essential experience listed here and treats the rest as helpful, not an automatic barrier.

Must have

  • 4+ years platform, MLOps, ML infrastructure, backend, or AI systems engineering experience
  • Strong Python and production engineering discipline
  • Experience with model serving, LLM APIs, orchestration, or workflow runtimes
  • Experience with observability, CI/CD, release gates, or production reliability
  • Practical judgment around safety, privacy, cost, and quality tradeoffs

Nice to have

  • Experience with local model serving, GPU inference, model quantization, or edge AI
  • Eval harness, prompt registry, or model governance experience
  • Experience with Langfuse, OpenTelemetry, vector stores, or model observability tools
  • Startup or high-change AI product environment experience

How you work

Lucy Labs looks for these working traits alongside technical experience.

Role DNA

Lucy Labs evaluates these traits as part of the fit for this role.

  • Platform-minded
  • Cost and reliability aware
  • Skeptical of unmeasured AI behavior
  • Strong systems operator
  • Comfortable owning invisible but load-bearing infrastructure
Next step

Apply for this role

The Lucy Labs application form opens with this role already selected. You can review the message before sending it.

Apply for this role

Frequently asked questions

Is this role open at Lucy Labs?

Yes. Lucy Labs confirmed this role is open on 25 August 2026.

Where does Lucy Labs base this role?

Lucy Labs bases this role in Madrid, Spain. The exact working arrangement is confirmed during the application conversation.

What does this role own at Lucy Labs?

At Lucy Labs, this role has one central responsibility: Owns model routing, versioning, eval execution and AI observability. The full description sets out the mission, responsibilities, and relevant experience.

How do I apply to Lucy Labs?

At Lucy Labs, use the application form. The role is selected automatically, and you can review it before sending.

Talk to Lucy