Payam Mousavi
Research Scientist / ML Scientist
I am a research scientist with 12+ years of experience bridging physics, engineering, and machine learning. I develop production-grade solutions in agentic systems, reinforcement learning, computer vision, and control systems across gaming, defense, energy, and logistics. I am experienced in leading R&D teams from research through deployment.
- Location
- Vancouver, British Columbia, Canada
- Website
- https://payam-mousavi.com
- PayamMousavi4
- pmousavi
Experience
– present
Senior Machine Learning Scientist at Electronic Arts
Technical lead on research projects for autonomous agents in 3D games within Quality Verification Services (QVS)
Highlights
- Developing reinforcement learning technologies for autonomous agent navigation and decision-making in 3D ARPG and FPS game environments
- Architecting agentic systems that integrate System I (fast/reactive) and System II (slow/deliberative) reasoning for complex 3D game scenarios
- Building tools to augment LLM-based agents with 3D spatial awareness and reasoning capabilities
- Extending theoretical foundations of state-space coverage to enhance and optimize automated game testing
– present
Applied Research Scientist at Alberta Machine Intelligence Institute (Amii)
Technical lead on multi-domain research projects with industrial clients in the Advanced Technology group
Highlights
- Led the Advanced Technology group, delivering ML solutions to industrial clients
- Created mathematical models and optimization software for plunger lift systems in oil & gas, reducing operational downtime and environmental impact
- Developed physics-informed neural network models for chemical process control in industrial settings
- Applied RL to a wide range of domains: industrial process control, multi-robot warehouse planning, active noise cancellation, VLSI routing, and analog circuit design
- Developed and deployed real-time control tools for the Drayton Valley Water Treatment Plant, directly interfacing with SCADA systems to optimize membrane cleaning
–
Staff R&D Scientist (Team Lead) at MDA Systems
Leading the AI Group in optics, ML for natural/satellite imagery, Earth Observation, and Command & Control
Highlights
- Designed and implemented GAN and VAE architectures to synthesize, manipulate, and perform anomaly detection on satellite imagery
- Developed software for detection, classification, and tracking of vessels in high-resolution optical satellite imagery
- Explored over-the-horizon communication concepts using laser-induced sodium layer scattering mechanisms
- Worked with Synthetic Aperture Radar (SAR) and high-resolution hyperspectral imaging data
–
Research Scientist at Phase Technology
Optical analyzers for cold-flow property measurement of hydrocarbons
Highlights
- Designed and optimized optical imaging systems using TracePro, COMSOL, OpenCV, and MATLAB
- Created automated tools to image and measure pour, cloud, and freezing points of liquids (e.g., jet fuel)
- Developed robotic arm control software (MATLAB, LabView, Python) for automated sample loading
- Applied machine learning techniques for liquid sample classification from optical measurements
–
PhD Candidate at Honeywell Automated Control Solutions (ACS)
Industrial terahertz imaging & spectroscopy for material composition analysis
Highlights
- Designed and built a terahertz spectrometer for non-destructive composition analysis of dielectric materials
- Developed mathematical models of the electromagnetic response of flat complex dielectrics in the terahertz spectrum
- Created an inference algorithm to determine material composition from optical measurements
- Developed a comprehensive statistical noise model that improved system measurement precision
- Contributed to the design and construction of the industrial alpha-prototype terahertz sensor
Education
–
PhD in Applied Physics from Simon Fraser University
–
MASc in Mechanical Engineering from University of British Columbia
–
BASc in Engineering Physics (Electrical Major) from University of British Columbia
Publications
MaskRenderer: 3D-Infused Multi-Mask Realistic Face Re-enactment , Pattern Recognition, vol. 157
A Novel Framework for Automated Warehouse Layout Generation , Frontiers in Artificial Intelligence, vol. 7
Human-in-the-Loop Reinforcement Learning: A Survey and Position on Requirements, Challenges, and Opportunities , Journal of Artificial Intelligence Research (JAIR), vol. 79, pp. 359-415
Applying Reinforcement Learning to Learn Best Net to Rip and Re-route in Global Routing , ACM Trans. Design Automation of Electronic Systems (TODAES), vol. 29(4), pp. 1-21
Multi-Robot Warehouse Optimization: Leveraging Machine Learning for Improved Performance , AAMAS 2023, pp. 3047-3049
RL-Ripper: A Framework for Global Routing Using Reinforcement Learning and Smart Net Ripping Techniques , ACM Great Lakes Symposium on VLSI (GLVLSI), pp. 197-201
A Real-time Bayesian Decision-Support System for Predicting Suspect Vehicle’s Intended Target Using a Sparse Camera Network , International Conference on Defense, Intelligence, and Security (ICDIS)
Maximum Likelihood Parameter Estimation in Terahertz Time-Domain Spectroscopy , Optics Express, vol. 29(4), pp. 4912-4926
Deep Learning for Vessel Detection and Identification from Spaceborne Optical Imagery , Ann. Photogramm. Remote Sens. Spatial Inf. Sci. (ISPRS), V-3-2021, pp. 303-310
Onboard Artificial Intelligence for Space Situational Awareness with Low-Power GPUs , 21st Advanced Maui Optical and Space Surveillance Technologies (AMOS)
Simultaneous Composition and Thickness Measurement of Paper Using Terahertz Time-Domain Spectroscopy , Applied Optics
A Novel Flow Reactor for Studying Reactions on Liquid Surfaces Coated by Organic Monolayers , The Journal of Physical Chemistry A, vol. 111(43)
Time Domain Spectroscopy (TDS)-Based Method and System for Obtaining Coincident Sheet Material Parameters , U.S. Patent 8,187,424
Continuous Referencing for Increasing Measurement Precision in Time-Domain Spectroscopy , U.S. Patent 8,378,304
Languages
- English
- Fluency: Native speaker
- Farsi
- Fluency: Native speaker
Skills
- Machine Learning
- Level: MasterKeywords:
- Domains
- Level: MasterKeywords:
- Languages & Tools
- Level: MasterKeywords:
- Leadership
- Level: MasterKeywords:
