Languages

PythonCC++JavaSQL

Libraries / Frameworks

LangChainLangGraphAmazon StrandsAmazon BedrockPyTorchTensorFlowNumPyPandasMpMatplotlibFastAPIFlaskSQLAlchemyPyMongo

Developer Tools

AWSGCPDockerKubernetesTerraformSpinnakerSplunkGrafanaGitGitHubMySQLMongoDB
Autodesk
Autodesk

Machine Learning Intern

Jan 2026 - Apr 2026
Montreal, QC
  • Created a reusable Agent framework in Python on Amazon Bedrock using the Amazon Strands SDK, enabling 6+ product teams to launch 50+ in-product Agent assistants with a shared architecture.
  • Standardized Agent tool access through MCP servers, reducing new tool integration time by 80% and eliminating duplicated tool wiring across teams.
  • Implemented token streaming for Agent responses, cutting time-to-first-output by 65% and improving interactive UX for production workflows.
  • Built a RAG pipeline using Amazon S3 for document and vector storage, enabling 6+ product teams to ingest 50,000+ chunks and improve relevant document retrieval by 55%.
  • Designed a token quota system and usage dashboard to track consumption across 50+ Agents and multiple model providers, reducing monthly token spend by 25%.
  • Deployed services to DEV, STG, and PRD with Spinnaker and Terraform, improving release reliability through infrastructure as code.
UKG
UKG

AI Software Developer Intern

May 2025 - Aug 2025
Montreal, QC
  • Engineered advanced Retrieval-Augmented Generation (RAG) pipelines in Python using LangChain and Google Vertex AI, improving document query relevance by 40%.
  • Automated ingestion of 10,000+ internal files by chunking and embedding into MongoDB with MySQL-backed metadata, streamlining RAG document retrieval.
  • Built and deployed 15+ task-specific Agents in Python by using LangGraph and LangChain, orchestrating REST APIs and internal tools via FastAPI to enable dynamic, goal-driven workflows.
  • Designed a modular Agentic RAG service that combined multi-step retrieval and reasoning, enabling agents to iteratively select and invoke multiple API tools, reducing incorrect or incomplete responses by 60%.
  • Applied Object-Oriented Programming to RAG and Agent architectures, enabling scalable orchestration, cleaner API integration, and more maintainable code.
  • Integrated a Redis-backed semantic caching layer to eliminate redundant LLM calls, cutting token usage by 60%, improving response speed by 23x, and saving $200K+ annually in inference costs.
  • Containerized all services with Docker and deployed across Kubernetes clusters, achieving 99.9% uptime.
  • Tested and documented RESTful APIs using Postman and Swagger to validate proper functionality.
Biomomentum Inc.
Biomomentum Inc.

Software Developer Intern

May 2024 - Aug 2024
Montreal, QC
  • Engineered a real-time signal processing pipeline in Python for biomechanical testing hardware, reducing latency by 80% via multithreading and algorithmic optimization.
  • Automated QA workflows in Python, cutting manual testing effort by 25% and enabling CI/CD integration.
  • Optimized custom VHDL code for Spartan FPGAs, increasing acquisition speed by 15%.
  • Programmed FPGA interfaces for ADS1298 ADCs and LSM9DS1 IMU with custom SPI, I2C, UART modules.
McGill Robotics

System Manager

Sep 2024 - Present
Montreal, QC
  • Led a 15-member software team, overseeing system architecture and improving task completion by 30%.
  • Assigned and tracked 15+ monthly tasks across the team.

Software Developer

Sep 2023 - Present
Montreal, QC
  • Built real-time coordination scripts and debugging tools in Python, C, and C++ enabling efficient control of 20+ hardware components.
  • Developed STM32 firmware in C for CAN communication reducing signal delay from 10ms to 3ms.
  • Engineered custom ESP32 remote kill switch in C++ reducing response time from 5s to <1s.
  • Designed Python scripts on NVIDIA Jetson GPU coordinating 20+ hardware components.
McGill AI Lab
McGill AI Lab

Machine Learning Researcher

Sep 2024 - Dec 2025
Montreal, QC
  • Designed and trained deep learning models in PyTorch and NumPy for MNIST digit classification, achieving 98%+ accuracy via dropout, batch normalization, and hyperparameter optimization.
  • Identified key performance bottlenecks using Matplotlib visualizations, improving model convergence rates.
  • Implemented data preprocessing pipelines with NumPy and scikit-learn to handle 60,000+ training samples, ensuring robust feature scaling and cleaner inputs for model training.
  • Experimented with multiple neural network architectures (CNNs, fully connected layers, regularization strategies) to benchmark trade-offs between accuracy and efficiency.
Marianopolis College
Marianopolis College

Teaching Assistant

Jan 2024 - Dec 2024
Montreal, QC
  • Graded assessments and assisted in delivering Professor Baharak Fatholahzadeh's college Physics courses for 150+ students.
  • [Fall 2024]
  • Waves, Light, and Modern Physics: Oscillatory Motion, Wave motion, Sound Waves, Superposition and standing waves, Ray Optics, Image Formation, Interference of waves, Diffraction, Relativity, Quantum Physics, Nuclear Decay, The Optics of the Compound Microscope.
  • [Winter 2024]
  • Electricity and Magnetism: Electric Fields, Electric Potential, Capacitance and dielectrics, Direct current circuits, Magnetic Fields and Sources, Faraday's Law and Inductance, Continuous Distribution of Charge.
McGill University

McGill University

B.Eng. Electrical Engineering, Minor in Applied AI

2023 - 2027
Montreal, QC

GPA: 3.8 / 4.0

Marianopolis College

Marianopolis College

Health Sciences

2021 - 2023
Montreal, QC

Dean's List both years enrolled