Work

Distributed Systems Intern @ Groq

Sep 2025 – Jan 2026

  • Headhunted based on open-source work at tinytpu.com
  • Optimized and deployed large-scale LLM inference pipelines using the compiler stack, focusing on throughput, latency, and KV-cache efficiency.
  • Engineered a load-balancing algorithm to maximize KV-cache hit rates and reduce hotspots, resulting in measurable API throughput gains under production workloads.

R&D Engineer @ Opal Camera

Mar 2025 – Jun 2025

  • Headhunted based on open-source work on OpenGhost, an aesthetic Pepper’s Ghost Display.
  • Engineered low-latency computer vision and integrated multiple sensors to enable real-time multimodal interaction with custom AI models on edge devices.

Machine Learning Consultant @ Condominium Authority of Ontario

Jun 2023 - Aug 2023 | Dec 2023 - Jan 2024 | May 2024 - Aug 2024

  • Enhancing categorization of survey responses and qualitative feedback analysis with natural language processing and text embeddings using Python.
  • Wrote Python scripts to classify survey responses by modifying the BERT LLM text classifier using TensorFlow.
  • Performed data cleaning and extraction of survey responses using Python and Pandas.
  • Created interactive maps and statistics of all Condominium Corporations in Ontario using Python, Pandas, Matplotlib, and Excel.

Undergraduate Researcher @ Diller Microrobotics Lab

May 2024 - Aug 2024

  • Received an NSERC Award to do research under the supervision of Prof. Eric Diller where I worked on designing instruments to enable bimanual magnetic control of microrobotic tools for surgery.

Undergraduate Researcher @ Free Appropriate Sustainable Technology Lab

Nov 2022 - May 2024

Research Assistant @ University Health Network

Jun 2021 - Sep 2022