An MS or PhD in control engineering, computer science, robotics, applied mathematics, mechanical engineering, or a related field is required.
Demonstrated expertise in AI development, scientific machine learning, optimal control, reinforcement learning, multi-agent systems, physics-informed machine learning, and optimization theory is required.
A strong technical background in control theory, model predictive control, state estimation, and system identification is required.
Strong programming skills in Python, C++, Swift, or a similar language are required.
Strong analytical, debugging, root-cause analysis, communication, and collaboration skills are required.
Responsibilities
Design and implement autonomous control strategies that use physics-based digital twins for prediction, optimization, and decision-making.
Translate comfort, energy, equipment life, and operational requirements into control objectives, constraints, and cost functions.
Develop scalable optimization algorithms using methods such as stochastic gradient descent, coordinate descent, distributed optimization, Bayesian methods, and evolutionary algorithms.
Design and implement physics-based automated fault-detection and diagnosis algorithms.
Develop fault-tolerant control methods that support degraded operation and system recovery.
Integrate control and learning algorithms into production systems while meeting reliability and real-time performance requirements.
Develop physics-informed predictive and learning models using deep learning, reinforcement learning, and transfer learning.
Develop autonomous agents, state-estimation methods, model adaptation, and control-correction algorithms.
Create learning methods that remain reliable under noise, outliers, sparse data, model uncertainty, and changing system behavior.
Define performance metrics, acceptance criteria, and automated tests for autonomous capabilities and levels of autonomy.
Test system behavior under disturbances, incomplete observations, model divergence, and equipment, sensor, or communication failures.
Verify fault-detection accuracy and validate fault-tolerant control, degraded operation, and recovery behavior.
Compare simulation results with analytical solutions, laboratory measurements, and real-building data.
Desired Qualifications
Experience with automatic differentiation and differentiable programming.
Experience with software design, design patterns, and software architecture.
Knowledge of building science, HVAC systems, thermodynamics, energy modeling, or grid-interactive controls.
Experience with software-in-the-loop and hardware-in-the-loop testing.
Experience with formal methods, probabilistic modeling, and graph neural networks.
Experience with building energy-modeling tools such as Dymola and EnergyPlus.
Experience in vector, SIMD, and tensor computational methods.
<p>Can you build intelligent systems that understand physical environments, make autonomous decisions, and demonstrate measurable real-world value? PassiveLogic is looking for a Physical AI Engineer to develop, optimize, and validate our autonomous control system, AI models, and levels of autonomy.</p><p><strong>About PassiveLogic</strong></p><p>PassiveLogic is the first fully autonomous platform for buildings. We’ve reinvented the fundamental principles of automation to democratize technology, optimize buildings, and reduce the world’s carbon footprint. We are a team of technologists, engineers, and creatives dedicated to making a sustainable impact through real-world solutions.</p><p>We are looking for team members who have a passion for technology and want to work on cutting-edge problems with real-world solutions. Our culture is built on bringing together the most talented engineers, thinkers, and creatives — backed by the world’s leading investors — working together to make the future a reality.</p><p><strong>About the Role</strong></p><p>You will develop and validate the algorithms that enable buildings to understand their physical state, learn from experience, and autonomously optimize their operation.</p><p>This role combines control theory, optimization, machine learning, physics-based simulation, and systems validation. Your work will span digital twins, autonomous reasoning, building physics, equipment behavior, and human comfort. You will develop production-quality algorithms and test them in simulation, laboratory systems, and real buildings.</p><p><strong>What You’ll Do</strong></p><p><strong>Develop Autonomous Control and Optimization</strong></p><ul><li><p>Design and implement autonomous control strategies that use physics-based digital twins for prediction, optimization, and decision-making.</p></li><li><p>Translate comfort, energy, equipment life, and operational requirements into control objectives, constraints, and cost functions.</p></li><li><p>Develop scalable optimization algorithms using methods such as stochastic gradient descent, coordinate descent, distributed optimization, Bayesian methods, and evolutionary algorithms.</p></li><li><p>Design and implement physics-based automated fault-detection and diagnosis algorithms.</p></li><li><p>Develop fault-tolerant control methods that support degraded operation and system recovery.</p></li><li><p>Integrate control and learning algorithms into production systems while meeting reliability and real-time performance requirements.</p></li></ul><p><strong>Develop AI and Learning Systems</strong></p><ul><li><p>Develop physics-informed predictive and learning models using deep learning, reinforcement learning, and transfer learning.</p></li><li><p>Develop autonomous agents, state-estimation methods, model adaptation, and control-correction algorithms.</p></li><li><p>Create learning methods that remain reliable under noise, outliers, sparse data, model uncertainty, and changing system behavior.</p></li></ul><p><strong>Validate Physical AI Systems</strong></p><ul><li><p>Define performance metrics, acceptance criteria, and automated tests for autonomous capabilities and levels of autonomy.</p></li><li><p>Test system behavior under disturbances, incomplete observations, model divergence, and equipment, sensor, or communication failures.</p></li><li><p>Verify fault-detection accuracy and validate fault-tolerant control, degraded operation, and recovery behavior.</p></li><li><p>Compare simulation results with analytical solutions, laboratory measurements, and real-building data.</p></li></ul><p><strong>What You’ll Bring</strong></p><p>If your experience does not meet all our posted requirements below, we’d still love to hear from you. We are looking for practitioners who are passionate about understanding people, committed to lifelong learning, and driven by the love of what they do. If that’s you, please apply!</p><p><strong>You Must Have</strong></p><ul><li><p>MS or PhD in control engineering, computer science, robotics, applied mathematics, mechanical engineering, or a related field.</p></li><li><p>Demonstrated expertise in AI development, scientific machine learning, optimal control, reinforcement learning, multi-agent systems, physics-informed machine learning, and optimization theory.</p></li><li><p>Strong technical background in control theory, model predictive control, state estimation, and system identification.</p></li><li><p>Strong programming skills in Python, C++, Swift, or a similar language.</p></li><li><p>Strong analytical, debugging, root-cause analysis, communication, and collaboration skills.</p></li></ul><p><strong>You Should Have</strong></p><ul><li><p>Experience with automatic differentiation and differentiable programming.</p></li><li><p>Experience with software design, design patterns, and software architecture.</p></li><li><p>Knowledge of building science, HVAC systems, thermodynamics, energy modeling, or grid-interactive controls.</p></li></ul><p><strong>It’s Helpful to Have</strong></p><ul><li><p>Experience with software-in-the-loop and hardware-in-the-loop testing.</p></li><li><p>Experience with formal methods, probabilistic modeling, and graph neural network.</p></li><li><p>Experience with building energy-modeling tools such as Dymola and EnergyPlus.</p></li><li><p>Experience in vector, SIMD, and tensor computational methods.</p></li></ul><p>We know there are candidates who might not fit everything we’ve described above, or who might have experience and skills we haven’t considered. PassiveLogic can sometimes be flexible enough to shift responsibilities to the right person, or otherwise identify open or upcoming roles that may better fit your professional background. Even if you don’t meet all the requirements above, we still want to hear from you.</p><p><strong>Compensation, Benefits & Perks</strong></p><ul><li><p>Competitive compensation</p></li><li><p>Generous equity package</p></li><li><p>Medical, dental, and vision coverage</p></li><li><p>Disability and life insurance options</p></li><li><p>Flexible paid time off</p></li><li><p>Team-building events</p></li><li><p>Free catered lunch in the office Monday through Friday</p></li><li><p>Free National Parks pass</p></li><li><p>Free ski pass—we’re located at the base of Big Cottonwood Canyon</p></li><li><p><em>Or </em>free<em> </em>ClassPass, access to fitness classes</p></li></ul><p><strong>When Applying, Include</strong></p><ul><li><p>A cover letter</p></li><li><p>A resume</p></li><li><p><em>Extra mile</em> — include a description of a project (of any type) you personally created, devised, built, managed, organized, or designed that was of your own self-initiative</p></li></ul><p><strong>Diversity and Inclusion</strong></p><p>Diversity, inclusion, and belonging is woven into our values and everything we do. We welcome all—come as you are and bring your whole self. We are proud to be an Equal Opportunity Employer. We celebrate diversity every day by maintaining a safe and inclusive environment for our employees at every stage of their careers.</p><p></p>