Professional Summary
Machine learning research engineer with a Ph.D. in control theory and optimization who blends rigorous mathematics, stochastic processes, and deep learning to deliver sensing and autonomy solutions. Develops novel algorithms for distributed systems, generative pipelines, and Bayesian inference, translating research breakthroughs into production-ready hardware and software. Proven first-author publication record and trusted partner across interdisciplinary teams.
Employment
- Research, invent, and implement novel ML algorithms for optical sensing technologies and HW platforms
- Develop deep learning models for sensor fusion and signal processing applications
- Use generative models to generate build corner cases; applied advanced statistical methods to match generated corner cases with limited existing data
- System-level prototyping, integration, characterization, and validation of ML-powered sensing solutions
- Cross-functional collaboration with mechanical, firmware, and test engineering teams to deliver state-of-the-art products
- Developed state-of-the-art algorithms for autonomous decentralized systems using advanced mathematics, graph theory, stochastic processes, and control theory
- Applied deep learning and reinforcement learning to dynamic systems with safety guarantees
- Designed distributed optimization algorithms for multi-agent coordination and area monitoring
- Published 4+ journal papers and 4+ conference papers in top-tier venues
Education
Thesis: Distributed Strategy Selection Over Graphs: Optimality and Privacy
Thesis: Privacy Preservation of Networked Systems
Deep Learning & Sequence Models, Probabilistic Learning, Bayesian Data Analysis, Optimization Methods, Algorithms, Optimal Control, Stochastic Processes, Real Analysis, Advanced Estimation and Detection
Key Research & Machine Learning Projects
- Integrated contraction theory with neural networks to learn accurate, stable dynamics models with safety guarantees
- Published in IEEE Robotics and Automation Letters (RA-L)
- Developed distributed algorithms for multi-agent systems to optimize resource allocation without central authority
- Applied to autonomous vehicle coordination and sensor placement problems
- Published in Automatica (2023) and IEEE Conference on Decision and Control
- Implemented Bayesian detection framework with RFID sensing for probabilistic target localization
- Applied Kalman and particle filtering for multi-robot localization using LiDAR data
Selected Publications
Internal Research
- Three internal deep learning papers for Apple research forums. Apple Internal Conferences. Specific details cannot be shared for privacy reasons.
Journal Papers
- "Distributed Strategy Selection: A Submodular Set Function Maximization Approach." Automatica, 2023.
- "Deep Contraction Control of Dynamic Systems." IEEE Robotics and Automation Letters, 2021.
- "A sub-modular receding horizon solution for mobile multi-agent persistent monitoring." Automatica, Vol. 127, 2020.
- "A study of privacy preservation in average consensus algorithm via deterministic obfuscation signals." IEEE Trans. on Control of Network Systems, Under Review.
Conference Papers
- "Distributed submodular maximization: Trading performance for privacy." IEEE Conference on Decision and Control, 2022.
- "Multi-Agent Maximization of a Monotone Submodular Function via Maximum Consensus." IEEE Conference on Decision and Control, 2021.
- "Privacy preservation in a continuous-time static average consensus algorithm over directed graphs." American Control Conference, 2018.
Technical Talks
- NeurIPS Safe and Robust Control of Uncertain Systems Workshop December 2021
- Southern California Control Workshop, UC Irvine October 2021
- IFAC Workshop on Distributed Estimation and Control in Networked Systems September 2019
- Southern California Control Workshop, UC Riverside May 2018
- American Control Conference June 2018
Technical Skills
Machine Learning & AI
Deep Learning, Reinforcement Learning, Neural Networks (CNN, LSTM, RNN), Transfer Learning, Bayesian Methods, Probabilistic Learning, Kalman & Particle Filtering
Mathematical Foundations
Optimization Theory, Submodular Optimization, Distributed Optimization, Control Theory, Graph Theory, Stochastic Processes, Real Analysis, Linear Algebra
Programming & Frameworks
Python, TensorFlow, Keras, PyTorch, C/C++, MATLAB, Java
Specialized Skills
Algorithm Design, System Identification, Multi-agent Systems, Sensor Fusion, Signal Processing
Honors & Awards
- Holmes Fellowship, UC Irvine MAE Department 2019
- Samueli Endowed Fellowship, UC Irvine MAE Department 2016
- Iran National Elite Foundation Fellowship 2009–2013
- Ranked 250th among 300,000+ participants in National University Admission Exam 2009