AI/ML Engineer

We’re looking for an AI/ML Engineer who wants to build ML driven automation for Luminary Cloud’s revolutionary physics simulation, analysis, and design cloud platform.

Work Areas:

• Conquer modeling problems that have not yet been solved, by Luminary or anyone else, from defining the problem out of a complex set of fuzzy constraints to specifying the data and components needed to build a solution, to championing the implementation of that solution and driving it forward.
• Conceptually identify the missing data needed to solve any particular modeling problem, and then build the data ingestion and preprocessing pipelines to obtain and extract the data.
• Devise the models that interpret sets of physical simulation outputs , with varying levels of uncertainty and noise, spanning over solids, liquids, and gasses; mechanics, aerodynamics, thermodynamics, and more; explore large parameter spaces intelligently to find the best design for objects moving through space and time; and optimize the performance of Luminary’s platform itself.
• Modernize computer-aided engineering by implementing these data pipelines, workflows, and models in Luminary’s platform, for engineering design of a limitless range of real objects used by all of us in everyday life, each with its own physical demands and dynamics.

Technologies and Tools:

• How to work with high-dimensional physically meaningful data, which may be sparse, and the strategies and approaches for optimization based on all of this data.
• Strong programming skills, including debugging, optimizing, and deployment.
• Comfort across machine-learning and data-science tooling, platforms, and services, as well as cloud-native systems engineering, especially GCP, and CI/CD deployment.
• Deep mathematical skill and intuition, with a working knowledge of machine learning, data engineering, deep learning frameworks, and related testing techniques.

We're looking for an engineer who has:

• Written substantial amounts of code that is running in production.
• Shipped a product with your code running in it, or shipped models to production.
• Designed models from scratch, iterating towards a production-quality model, and characterized the various tradeoffs relevant to the application context (e.g., performance versus accuracy).
• Led or was closely aligned with leading data acquisition in a modeling context, including identifying what missing data was needed to build effective models and being involved in acquiring that missing data.
• Worked with physically meaningful data, preferably from physical-science-based simulations, and performed uncertainty quantification.
• Owned large projects end-to-end, and filled an IC role as a driver of complex multifaceted technical efforts.