Abtin Aryanpour

Resume

Abtin Aryanpour
Computer Engineering, University of Waterloo

Open the PDF in a new tabDownload it (one page, 122 KB)

Education

University of Waterloo

September 2026 to April 2031

Waterloo, ON. Candidate for BASc in Computer Engineering, Co-op Program.

Technical skills

Languages
C, Python, C++, Java, JavaScript, SQL
Embedded and DSP
Pico SDK, Arm Cortex-M33, PIO, DMA, I2S, PWM, watchdog, fixed-point math, FFT, log-mel
ML and vision
PyTorch, scikit-learn, OpenCV, NumPy, CNNs, Gaussian mixtures, int8 quantization, RANSAC
Tools and platforms
Git, GitHub Actions (CI), CMake, pytest, Django, SQLite, AWS EC2

Experience

Autonomy Software Member

September 2026 to now

Waterloo Aerial Robotics Group, Waterloo, ON

  • Built a Python stitcher (PyTorch, OpenCV, XFeat, RANSAC) that merges out-of-order, GPS-tagged photos from 3 drones into one georeferenced map. Sole developer, merged with 130 tests.
  • Designed a least-squares pose refinement that cut mean simulated misalignment from 13.6–69.8 cm to 4.0–8.3 cm.
  • Solved feature matching across 180° row turns, then used drone yaw to extract features once per photo, cutting simulated time per photo from 0.42–0.75 s to 0.13–0.19 s.
  • Implemented lens undistortion and blur, exposure and tilt checks that keep unusable photos out of the map.
  • Built a swarm-spacing module (Lloyd’s algorithm, Voronoi cells, Shapely) that spreads drones evenly over concave, GPS-bounded fields, cutting spacing variation (CV) from 0.46 to 0.06 in simulation.

Homework Helper and Assistant Teacher

September 2022 to July 2025

Spirit of Math Schools Inc., Richmond Hill, ON

  • Ran a drop-in homework classroom as one of two staff (2024–2025), helping about 30 students per session.
  • Taught 1–2 classes a week of up to 16 students (2022–2024), covering lessons and contest-style algebra.

Projects

Python, C, Raspberry Pi Pico 2

  • Developed a Pico 2 andon system that hears a fault through an I2S mic and cuts the fan’s power via a MOSFET, stopping each of 3 real fans by itself 3.461–11.661 s after an injected fault.
  • Wrote real-time C firmware (I2S capture via PIO and DMA, FFT log-mel features, per-fan Gaussian mixture scoring) that matches Python’s scores on the board at 1.684 ms per 32 ms audio frame.
  • Trained a PyTorch CNN on healthy audio only, reaching 92.13% mean AUC on held-out DCASE 2020 data against 79.70% for the baseline autoencoder I reproduced.
  • Proved the model hears more than loudness: with volume matched it still caught both real-fan faults at 100% AUC, while a level meter reached only 63.34% AUC on the DCASE dev set.
  • Quantized the CNN to int8 (383.0 KB to 98.7 KB at 92.08% AUC) and ported it to C, bit-exact with Python on the Pico 2’s Cortex-M33.

Python, Django, JavaScript, Tailwind CSS

  • Built a full-stack forum as the only developer on a 3-person team using Django, jQuery (AJAX) and SQLite, winning 1st of 32 teams at CNLC 2025.
  • Implemented voting, sorting, filtering and fuzzy search (Fuse.js) through JSON endpoints, with no page reloads.
  • Secured accounts with Django auth, CSRF protection, reCAPTCHA and moderator roles, and deployed on AWS.

Awards

  • Canadian National Leadership Conference: 1st place (2025) and 4th place (2024), Coding & Programming
  • Waterloo Math Contests, 2025–26: Euclid (86/100), Hypatia (33/40) Honour Roll; Fermat, CSMC Distinction
  • Bayview Secondary School: Excellence in Mathematics (2025, 2026)
The one-page resume PDF: education, technical skills, experience (Waterloo Aerial Robotics Group and Spirit of Math), projects (Andon and CyberShield) and awards.

The same page as the PDF. Click it to open the PDF, where the links work.