Research Engineer - Evaluations

Luma
Redwood City
Workplace: HybridFull timeUSD 190,000 - 375,000 annuallyFunction: Research & Scientific (R&D)Experience: 5+ yearsEducation: mastersSkills: []

Own the infrastructure and pipelines that evaluate Luma’s generative models and close the loop between model outputs, measurement, and improvement. Build automated evaluation systems across image, video, text, and audio, define metrics grounded in human intent, and integrate evaluation signals into training loops such as reinforcement learning and reward modeling. Deliver large-scale regression testing, benchmarking, monitoring, and the dashboards/alerts researchers and teams rely on.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Luma
Luma
1 week ago

Research Engineer - Evaluations

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 4 hours agoStatus: Live

Job Summary

Own the infrastructure and pipelines that evaluate Luma’s generative models and close the loop between model outputs, measurement, and improvement. Build automated evaluation systems across image, video, text, and audio, define metrics grounded in human intent, and integrate evaluation signals into training loops such as reinforcement learning and reward modeling. Deliver large-scale regression testing, benchmarking, monitoring, and the dashboards/alerts researchers and teams rely on.
Location: Redwood City
Workplace: Hybrid
Employment Type: Full time
Job Function: Research & Scientific (R&D)
Seniority: Mid level

Key Responsibilities

  • •Design and build scalable pipelines for automated evaluation of generative models across image, video, text, and audio.
  • •Develop metrics and evaluation models for fidelity, coherence, temporal consistency, and alignment with human intent.
  • •Integrate evaluation signals into training loops, including reinforcement learning and reward modeling.
  • •Build infrastructure for large-scale regression testing, benchmarking, and monitoring of multimodal models.
  • •Collaborate with researchers running human studies and maintain dashboards, reporting, and alerting for evaluation results.

Pay and Benefits

Salary: USD 190,000 - 375,000 annually
Equity and Bonus:Equity
Perks:Equity

Key Requirements

  • •5+ years building ML evaluation systems, model pipelines, or large-scale infrastructure.
  • •Master’s or PhD in Computer Science, Machine Learning, or related field, or equivalent industry experience.
  • •Proficiency in Python and an ML framework (PyTorch, JAX, or TensorFlow).
  • •Hands-on experience with visual data (image and/or video) in evaluation, modeling, or data prep.
  • •Strong software engineering skills across CI/CD, testing, data pipelines, and distributed systems.
Experience:5+ yearsGenerative AIMultimodalHuman-in-the-loopModel evaluationReinforcement learningReward modeling
Education:Master's in Computer Science, Machine Learning, or a related field
Tech Stack:PythonPyTorchJAXTensorFlowCI/CDReinforcement learningReward modelingDiffusionLLMsDistributed systemsDashboardsBenchmarkingMonitoringRegression testing

Company Brief

Luma
Develops AI-powered tools for capturing, editing, and rendering high-quality 3D scenes from photos and videos, enabling creators to generate photorealistic 3D assets and spatial experiences.
Industry: AR/VR & Spatial Computing
Website