Boris Tomov

I am a recent UC Berkeley graduate in Data Science with a strong focus on robotics, software engineering and machine learning. Currently in the first year of my three-year OPT, I am eager to grow as a robotics professional by working on intelligent systems that combine robotic training, perception, and decision-making. My goal is to contribute to the development of machines that can learn and adapt to real-world environments while also expanding my expertise through hands-on industry experience. I see this period as an opportunity to build a foundation for long-term impact in the field of robotics and AI.

I have focused on advancing general-purpose robotics by applying machine learning, with a particular emphasis on imitation learning. My work involves developing autonomous systems that integrate perception, control, and decision-making, enabling robots to acquire skills from demonstrations and generalize them to unstructured environments. I have gained hands-on experience designing robotic behaviors that combine adaptability with reliability, pushing robotics beyond narrow, task-specific applications.

In practice, this has included projects such as building teleoperated manipulators and autonomous mobile platforms that leverage computer vision, trajectory optimization, and ML-driven control. I have worked with frameworks like ROS, PyTorch, and TensorFlow to implement learning-based control pipelines and have applied computer vision tools such as MediaPipe and OpenCV for real-time robotic perception.

I am particularly motivated by the vision of robots that can operate alongside humans in meaningful ways—learning tasks, adapting across contexts, and supporting real-world automation challenges. Currently in the first year of my three-year OPT, I am seeking opportunities to grow in robotics and AI, with the goal of building intelligent systems that bridge research and deployment for lasting impact.

I hold a B.A. in Data Science from the University of California, Berkeley, with an emphasis in Robotics and Machine Learning. My coursework combined a strong foundation in mathematics, computer science, and engineering with advanced robotics and AI. Core classes included EECS 16A & 16B (Designing Information Devices & Systems), CS 61A (Structure and Interpretation of Computer Programs), CS 61B (Data Structures), and CS 170 (Efficient Algorithms), which grounded me in systems, algorithms, and programming fundamentals. Building on this, I completed Stat 134 (Probability), CS 189 (Machine Learning), CS 188 (Artificial Intelligence), and Data C182 (Ethics, Policy, and Deep Learning), where I studied probabilistic modeling, supervised and unsupervised learning, reinforcement learning, and neural network–based approaches to AI. To complement these, I took EECS 106A (Introduction to Robotics) and ME 135 (Design of Microprocessor-Based Mechanical Systems), which emphasized hands-on robotics, control systems, and hardware-software integration. Collectively, these courses shaped my academic focus on developing intelligent robotic systems that combine perception, learning, and control.