Alexiy Buynitsky

whoami

Hey!! I'm Alexiy, an incoming MS student in CSE at UCSD (Graduted from Purdue with a BS in CS and Math May '25!) with an unbreakable caffeine addiction (even full-timers at SpaceX were concerned...).

I love learning anything new and learn best by getting my hands dirty. For me, the best feeling in the world is when something works/clicks after bashing my head against a problem for hours or even days.

In my free time, I love hiking / mountain biking / skiing, and finding excuses to visit coffee shops.

Feel free to reach out!!

~/random_facts.md

Favorite Quotes

"If you are not in pain, you are not learning.", "FAFO", "FIFI" - ppl @ SpaceX
"Who needs drugs when you have Engineering" - Stuff Made Here
"[Insert Algo Question]. Provide a brief but precise explanation" - CS 251/381 exams
"Oooooh yea I don't like this problem. It came off a graduate qualifying exam. I put it on there just to torment people, even I don't know how to do it" - MA 453 Prof
"[Discussing logs of complex #s]... Unfortunately zero is still F***ed. I don't know how to take log of zero" - MA 425 prof
"Next friday you are gonna be tired after midterm so we gonna do some goofing [goofing = deriving RSA]. Enjoy your weekend but not too much." - CS 182 prof
"[Talking about CS251 exam] Yes, I added this question to troll kids" - CS251 Head TA
"Oh right I remember now. This problem wasn't solvable last time I took the course" - CS 587 TA

Favorite Coffee Shops

Mount Currie Coffee Co in Whistler B.C.
Schat's Bakery in Mammoth Lakes
Philz Coffee in Sunnyvale

Favorite Hikes

Sahale Arm / Cascade Pass in Northern Washington
Garibaldi Lake in B.C
Lake Ediza - Iceberg Lake - Thousand Island Lake loop in Eastern Sierra

Foreign Languages

Ukrainian
Russian
a bit of Spanish

Favorite Books

The Martian & Project Hail Mary by Andy Weir
Algebra, Topology, Differential Calculus, and Optimization Theory for CS & ML by Gallier & Quaintance

~/Experience.md

Incoming ML Intern @ Persona AI Houston | May 2025

Undegraduate Researcher @ CoMMA Lab Purdue | Aug 2023 - Present

Conduct research on Behavioral Cloning & Active Vision for manipulators under the supervision of Professor Zachary Kingston.
Achieve 200x speedup for generating expert trajectories for point-to-point motion planning in tabletop environments through RRTConnect using hardware-accelerated planning (VAMP)
Extend MπNets to learn point-to-point motion planning in occluded environments with Behavioral Cloning from expert trajectories generated by VAMP

AI Engineering Intern @ Armada AI Remote | Oct 2023 - May 2025

First Intern at Armada AI building Edge AI Applications for remote compute hardware
Develop spatially-aware Code-as-Policies methods for controlling PTZ Cameras on the edge
Perform model distillation by generating synthetic data and finetuning LLMs using SFT and DPO
Developed VLM/LLM VideoQA agent for real-time video Q&A for security camera footage

Undegraduate Researcher @ CoRAL Lab Purdue | Aug 2023 - May 2025

Conducting research on robotic learning under the supervision of Professor Ahmed Qureshi
Researching Motion Planning in dynamic environments via Active NT Fields and Sign Distance Fields
Extended Unitree simulator to support Unitree B1 Quadruped Robot in Gazebo and PyBullet
Teaching robots to navigate through Purdue with custom knowledge using LLMs, RAG, and vector databases

Engineering Intern @ SpaceX Redmond | May 2023 - Aug 2023

Develop robotic solutions for quicker manufacturing and assembly of Starlink satellites
Prototype satellite assembly cells, working with 6-axis robotics arms, CV, actuators, sensors, & safety hardware
Achieve 80x speedup between PLC & CV software by developing a TCP-style communication library

TensorFlow Model Developer @ Google x Duality Lab Purdue | Jan 2023 - May 2023

Building data pipeline for Maskformer and Mask2former using Google Deeplab2 and Tensorflow
Generate, decode, and load TFRecords for panoptic segmentation from COCO dataset with Bash and Python
Apply random-cropping and color jitter to images/masks, create project config and data loaders
Achieving < 0.01% difference between PyTorch and Tensorflow implementations through differential testing

Rocket League Software Developer @ Autonomous Robotics Club Purdue | Apr 2022 - Dec 2022

Refactor sim to better reflect real-world conditions by randomizing physics dynamics, tuning car properties
Simulating latency with Rospy and ROS

Signal Processing Intern @ SunScool Sunnyvale | Apr 2022 - Aug 2022

Trim, normalize, and denoise voiceovers from 80+ chapters with noise profiles, High and Low Pass filters
Adjusted audio volume and determined parameters for audio voice overs with FFmpeg and SOX

~/publications.md

Liu, Y., Buynitsky, A., Ni, R., and Qureshi, A.H., 2025. Physics-informed Neural Motion Planning via Domain Decomposition in Large Environments. Published in 2025 IEEE International Conference on Intelligent Robots & Systems (IROS)

Chen, W., Liu, Y., Buynitsky, A., and Qureshi, A.H., 2025. Self-supervised Hierarchical Robot Navigation Policy Learning using Physics Priors in Unknown Environments. Published in 2025 IEEE International Conference on Intelligent Robots & Systems (IROS)

Buynitsky, A., and Kingston, Z., 2025. Faster Behavioral Cloning with Hardware-Accelerated Motion Planning. Published in RoboARCH Workshop at 2025 IEEE International Conference on Robotics & Automation (ICRA)

Buynitsky, A., Ehsani, S. and Mishra, P.K., Armada Systems Inc, 2025. Robotic Control Using Natural Language Commands U.S. Patent 12289517 B1.

Buynitsky, A., Ehsani, S. and Mishra, P.K., 2024. Camera Control at the Edge with Language Models for Scene Understanding. Published in 11th International Conference on Control, Automation and Robotics (ICCAR)