Software engineer specialized in machine learning (especially deep learning and reinforcement learning).

Also have significant experience in embedded systems, high performance computing, hardware/software interfacing, graphics, computer vision, and electronics design.

High proficiency in C++11/14.

Professional Experiences

• Engineering for machine learning research

• Interaction Networks for Learning about Objects, Relations and Physics

  • papers.nips.cc/paper/6418-interaction-networks-for-learning-about-objects-relations-and-physics

• AlphaGo Project

  • deepmind.com/research/alphago

• AlphaZero Project

  • arxiv.org/abs/1712.01815

• Embedded C++ development with a talented team that puts a lot of emphasis on doing things right (low technical debt)

• Developed firmware for HD IP surveillance cameras with ARM Cortex-A9 CPU on a specialized SoC

• Wrote, maintained, and debugged highly parallel code with complex synchronization requirements and a Linux kernel driver for controlling lenses with electronic focus

• Post-silicon bringup of Kepler generation graphics processor units (GPU)

• Binning and characterization of GPUs (performance spread at different voltages and temperatures)

• Performed high frequency signal integrity, power sequencing, and PLL tests

• Analyzed and "hacked" PCB designs to change the order power rails come up, etc

• Designed and implemented a self-adjusting head restraint that senses the occupant's head position and adjust the head restraint to maintain optimal distance in real time to minimize whiplash in case of collision

• Completed the entire electrical system from system design, component spec-ing, schematics/PCB design, assembly, firmware programming (thousands of lines of code including a custom multi-tasking system), to testing, on a very tight schedule

• Designed multiple 2 layer PCBs with analog electromagnetic sensing circuitry, ARM Cortex-M3 (STM32) MCU, brushless motors commutation and control, and USB interfacing

• Delivered a reliable system that successfully met all requirements and provided thorough formal documentation

• Implemented a major feature in a cross-platform C++ game, "Dead Rising 2: Case West", that involved scene analysis, heuristics, front-end, audio, rendering, and animation support

• Collaborated with game designers closely to deliver the feature exactly as envisioned, on a very tight schedule, with constantly evolving requirements

• Developed C# tools to improve QA, artists, and programmers efficiency

Technical Projects

• Used multiple deep neural networks with temporal-difference reinforcement learning to play chess

• Implemented neural networks and stochastic gradient descent (AdaDelta) in C++11 using the Eigen BLAS library

• Engineered a smooth low level feature representation that resulted in highly efficient learning with good generalization

• Devised a novel way to combine the power of minimax searches in stochastic situations with the power of neural networks in pattern recognition

• The resulting program plays at the level of FIDE International Master after 72 hours of training - by far the highest strength ever achieved using machine learning from low level features

• Results were widely reported in both mainstream and tech media, including the MIT Technology Review

• Thesis: http://arxiv.org/abs/1509.01549

• Used deep learning techniques to segment 3D brain MRI images for Alzheimer's diagnosis

• Implemented 3 convolutional architectures in Theano (Python meta-programming framework) with different computational power vs accuracy tradeoffs, and performed experiments on GPUs

• Wrote a report summarizing the development history of neural networks, including recent discoveries such as ReLU activation, DropOut, model compression ("Dark Knowledge"), and convolutional architectures

• Report: http://arxiv.org/abs/1505.02000

• Designed a team of autonomous robots to play at the annual Robocup international robot soccer competition

• Led an electrical sub-team of about 10 students responsible for all electrical aspects of the robots

• Mentored younger students working on parts of the robot as well as peripheral projects and experimental tech prototyping

• Kept track of electrical budget, timelines, and collaborating with other sub-teams (mechanical and software)

• http://ubcthunderbots.ca

• Wrote a CG fly-through video of an airplane performing aerobatics above a complex randomly-generated cityscape

• Final project of an introduction to graphics course (140% on this project, 100% in the course overall). Orders of magnitude higher complexity than all other submissions

• Implemented custom GLSL shader-based, high quality lighting, particle effects, variably-emissive surfaces, and fog

• Implemented an efficient renderer to support very large scale cities (500,000 buildings in one frame)

• http://www.youtube.com/watch?v=_aF4uGe3jMQ&hd=1 (http://tinyurl.com/kyxpc33)

• Built a simple robot that collects tennis balls and push them out of the opponent's gate

• Responsible for all software components - C++/Qt-based GUI and an AI based on a hybrid of potential well and A-star algorithms

• Wrote a realistic simulator that allowed us to work on the AI before we had working hardware

• AI worked perfectly and transferred to real hardware almost without any change

• Oversaw hardware and firmware design, and system integration

• Wrote an interactive bot that provides computer analysis of chess positions on the Free Internet Chess Server

• Designed a convenient "chat" based user interface that allows users to tell the bot to provide real-time analysis on ongoing games, or annotate historical games

• Used BSD sockets API to talk to the server using a difficult-to-parse human-oriented protocol

• Uptime of about 5 years. Used by more than 32000 unique users

• https://bitbucket.org/waterreaction/analysisbot

Education

Interests

• Classical musician on the clarinet, saxophone, piano, and viola, with 3 years of orchestra playing experience

• Backpacking, blogging, social psychology and mental health, musical theatre, martial arts, fish-keeping, video games, consumer gadget design, chess, SCUBA diving

• Federal Aviation Administration and Transport Canada certified private pilot (airplane)