Andrew Nash

Aurrigo · Staff ADS Engineer – Autonomy Lead

• + Led autonomy for Canada's first medium-speed autonomous shuttle

  Team of 6. Core author and code owner of two $1M+ production deployments. [press]

• + Built an airport digital twin 50x faster than CARLA

  Real-time aircraft turnaround with vehicles, people and baggage. Every AV sensor simulated in CUDA, with LiDAR 6x faster than NVIDIA's renderer on the same GPU.

• + Authored production localization at 5 cm lateral accuracy

  Real-time GNSS, LiDAR and IMU sensor fusion, live at 5 sites on 4 vehicle platforms.

• + Authored a CUDA LiDAR perception pipeline

  Occupancy mapping, SLAM and obstacle clustering in real time: 5 ms per scan on 0.1 CPU core.

• + Shipped camera-LiDAR 3D object detection at 83.4 mAP @ 20 Hz

  Trained in PyTorch, deployed as TensorRT inference on the vehicle with an ISO 26262 redundant safety channel.

• + Architected the fleet dashboard

  Real-time WebGPU rendering of HD maps, live sensors, plans and vehicle views at a steady 60 FPS.

ROS · C++ · Python · CUDA · PyTorch · TensorRT · GTSAM · Linux

Aurrigo · ADS Team Lead, North America

• + Solo-authored LiDAR SLAM and mapping for 50+ km/h autonomy

  C++ GTSAM factor graph built on GLIM, fusing LiDAR, IMU and GPS.

• + Authored real-time C++ motion planning and control

  400+ candidate trajectories at 50 Hz, selecting the smoothest safe path.

• + Built Aurrigo's first AV simulator in Unreal Engine

  1,000s of safety cases for airport customers.

ROS · C++ · Python · GTSAM · SLAM · Unreal Engine · CI/CD

Co-op internships · ML, data science and NLP

• Nasdaq (Verafin) Machine Learning Engineer · May – Aug 2021 Lifted gradient-boosting fraud-detection model precision by 6 pp at fixed recall.
• Bank of Canada Data Science Developer · Sept 2020 – Apr 2021 Built anomaly-detection models automating economist data-review workflows.
• IBM NLP Developer · Jan – Apr 2020 Improved enterprise semantic matching by 8% via weighted word embeddings.
• Royal Bank of Canada Full Stack Data Scientist · May – Aug 2019 Built a full-stack semantic search prototype with an NLP backend and web frontend.
• BlackBerry QNX NLP Developer · Sept – Dec 2018 Applied NLP classifiers to automate software-license tagging across QNX repos.

Sage · Real-time D&D AI co-pilot

• Live voice agent: per-player streaming speech-to-text, an LLM over 53 MCP tools and hybrid RAG.
• Distilled a 66M DistilBERT gate from the LLM that decides when to speak, in 70 ms on CPU.
• Fine-tuned Qwen LoRAs from 1.7B to 27B to frontier-API card quality.

PyTorch · LLM · LoRA · RAG · MCP · FastAPI realtime voice →distillation →fine-tuning →

IGVC · Autonomous vehicle competition

• Trained custom transformer BEV prediction models from Unreal Engine data.
• Design placed 2nd internationally.

ROS · Unreal Engine · C++ · PyTorch write-up →

SR AUV · Autonomous underwater vehicle

• Real-world tested, flying end-to-end autonomously using PPO RL.
• Awarded best 2021 capstone project.

Unity · C# · TensorFlow · TPU · RL write-up →

SpaceX Hyperloop · Pod competition

• Top 2.6% worldwide, 3rd in North America. Built full-stack pod telemetry.

C++ · Flask · JS · Protobuf · CAN

Herd's Eye View · AIIDE-2023

Improving game-AI agent learning with collaborative perception. MSc thesis.

Unity · RL · Transformer · PyTorch arXiv →write-up →

MSc Computer Science (Thesis)

Memorial University of Newfoundland. 4.0 GPA. Thesis: Herd's Eye View (AIIDE-2023).

BEng Computer Engineering (Co-op)

Memorial University of Newfoundland. Capstone: SR AUV, best 2021 capstone.