Machine Learning Engineer

Focused is seeking a Machine Learning Engineer in Austin, TX to work at the intersection of machine learning engineering and computational physics. The role applies data-driven methods to advance the company’s Digital Twin architecture for clean energy and fusion programs, including model development, deployment, and integration with simulation and sensor data.

Responsibilities

• Design and deploy surrogate models and reduced-order models (ROMs) that replace or accelerate high-fidelity multiphysics simulations within the Digital Twin environment
• Develop physics-informed machine learning (PIML) and physics-informed neural networks (PINNs) that embed physical constraints including Maxwell’s equations, thermodynamics, and fluid dynamics into model architectures
• Build and maintain machine learning pipelines for training, validation, uncertainty quantification (UQ), and ongoing model refinement using experimental and simulation data
• Implement active learning and Bayesian optimization workflows to support design space exploration while reducing costly simulation runs
• Integrate trained ML models into the broader Digital Twin framework, connecting with HPC simulation outputs (COMSOL, ANSYS, and custom solvers) and real-time sensor data
• Develop anomaly detection and predictive diagnostics models to monitor system health and identify off-nominal behavior in laser subsystems
• Apply reinforcement learning and Bayesian control approaches to enable autonomous or semi-autonomous optimization of laser operating parameters
• Collaborate with Digital Twin architects, systems engineers, and optical simulation scientists to ensure ML models satisfy fidelity, latency, and uncertainty requirements
• Establish best practices for model versioning, reproducibility, testing, and documentation in a fast-moving research environment

Requirements

• Master’s or PhD in Machine Learning, Computational Physics, Applied Mathematics, Data Science, Computer Science, or a closely related field
• Proven experience building, training, and deploying ML models for complex physical systems, including strong deep learning skills with PyTorch and/or TensorFlow/JAX, along with probabilistic modeling and uncertainty quantification
• Expert-level Python; proficiency in C++ or Fortran is a plus; experience working with HPC environments, including batch schedulers and MPI/OpenMP parallelization
• Fluency working with PDE-based simulation outputs, time-series sensor data, and high-dimensional parameter spaces common in multiphysics applications
• Hands-on experience with Gaussian processes, neural network surrogates, reduced-order models, or comparable metamodeling techniques
• Experience building robust ML pipelines for scientific data, including preprocessing, feature engineering, validation, and deployment
• Ability to clearly communicate model behavior, confidence intervals, and limitations to physicists, engineers, and non-ML specialists
• Strong cross-functional collaboration skills in an interdisciplinary setting spanning physics, engineering, and software

Technologies

• PyTorch, TensorFlow, JAX
• C++, Fortran
• COMSOL, ANSYS
• MPI, OpenMP
• Gaussian processes
• NVIDIA Omniverse, Siemens Xcelerator, ANSYS Twin Builder
• DeepONet, FNO
• MLflow, Weights & Biases, DVC

Benefits

• Competitive salary and company ownership through stock options
• Medical, Dental, Vision with multiple plans active on the 1st day of employment
• Unlimited PTO
• Healthy snacks and drinks
• 401k plan with match up to 4% on top of the employee contribution
• State-of-the-art Windows or Apple laptops plus additional equipment including keyboard, mouse, and headset
• Regular events to support team bonding and collaboration

Nice-to-Haves

• Experience with physics-informed neural networks (PINNs) or neural operators (DeepONet, FNO) applied to physical systems
• Background in laser physics, plasma physics, high-energy-density science, or related complex physics domains
• Experience with digital twin platforms and live integration of ML models with simulation environments (including NVIDIA Omniverse, Siemens Xcelerator, ANSYS Twin Builder)
• Familiarity with multidisciplinary design optimization (MDO) workflows such as Design of Experiments (DoE), sensitivity analysis, and uncertainty propagation
• Experience applying reinforcement learning to physical system control or optimization
• Familiarity with Monte Carlo methods and statistical uncertainty quantification frameworks
• Experience applying MLOps tools (MLflow, Weights & Biases, DVC) in a scientific computing context
• Interest in fusion energy, advanced laser systems, or high-energy-density physics

What We Offer

• Innovative Technology & Mission: contribute to clean energy and scientific discovery through cutting-edge research
• Career Development: join an early, growing company focused on investing in people and advancing new technology
• Collaborative Culture: work in a dynamic, international environment with top-tier scientists and engineers
• Ownership: take ownership from day one and drive impact through decision-making and problem-solving
• Your Success is our Success: competitive compensation and stock options aligned with company ownership
• Medical, Dental, Vision: multiple plans available and active on the 1st day of employment for employees and enrolled dependents
• Vacation Days: unlimited PTO
• Snacks and Drinks: office fridges stocked with healthy snacks and drinks
• Retirement Plan: 401k match up to 4% on top of employee contributions
• Equipment: state-of-the-art Windows or Apple laptops plus core peripherals from day one
• Events: regular events supporting team bonding, collaboration, and company culture