Machine Learning Scientist

Description

• Design algorithms to estimate concentration gradients, source localization, and spatiotemporal plume dispersion.
• Global impact: Help scale new materials and energy solutions that reinforce industrial resilience across the U.S. and Europe.
• Implement physics-informed ML methods (e.g., CFD-informed priors, Gaussian plume models, graph neural networks for spatial grids).
• Develop and deploy ML models for detecting and quantifying airborne compounds from multivariate gas sensor data.
• Validate models using both simulated and real-world datasets; design experiments to improve detection accuracy and robustness.
• Build scalable systems for real-time sensor data ingestion, preprocessing, and fusion across large sensor arrays.
• Create 3D visualization tools for mapping gas dispersion and dynamics in the environment, integrating data from a distributed grid of sensors.
• Work in a cross-disciplinary team combining embedded systems, cloud architecture, and applied ML.
• Collaborate with hardware and embedded systems engineers to ensure ML pipelines are optimized for field deployment.
• Cutting-edge innovation: Work on technologies at the intersection of materials science, energy storage, and advanced manufacturing that strengthen energy security and local supply chains.
• Prototype and refine 3D mapping tools that enable end-users to monitor airborne compound plumes as volumetric “cloud maps.”

Requirements

• Strong proficiency with Python, TensorFlow/PyTorch, and data visualization libraries.
• Familiarity with edge ML deployment (TensorRT, ONNX Runtime, etc.).
• Strong background in machine learning for time-series and multivariate sensor data.
• Teamwork and culture: Experience a workplace built on trust, respect, and shared success — where collaboration fuels breakthroughs and everyone’s ideas are heard.
• Experience with computational fluid dynamics (CFD), plume dispersion models, or environmental modeling.
• US Citizen or Permanent Resident due to Export Control/ITAR
• Ability to integrate physics-based models with data-driven ML approaches.
• Track record of publishing, prototyping, or deploying advanced sensing/ML systems.
• Experience with Bayesian inference, spatiotemporal statistics, or probabilistic graphical models.
• Strong data storytelling skills and ability to communicate complex results with intuitive visuals.
• Familiarity with distributed sensor networks, IoT data pipelines, and real-time analytics.
• Doctorate degree in a relevant field (e.g., chemistry (molecular), materials science, mechanical engineering, electrical engineering, and chemical engineering, computer science)
• Expertise in 3D data visualization (e.g., Unity, WebGL, Three.js, ParaView, or similar frameworks).
• Knowledge of GIS systems, spatial data indexing, or large-scale environmental datasets.

Benefits

• Extraordinary people: Join a team of talented, friendly, and down-to-earth innovators who support, challenge, and inspire one another every day.
• Career growth: Be part of a fast-moving company entering a commercial growth phase, with opportunities to lead, learn, and make your mark.
• Opportunity to pioneer next-generation environmental sensing systems.

Training + Development

Interview process

Visa Sponsorship

Security clearance