AI Engineer|
Toronto, Canada
Hi! I'm Shirin
A Machine Learning Researcher & Engineer based in Canada. I have been working on Reinforcement Learning applications for the past 4 years, currently I am more focused on Post Training Optimization and Validation!
- Verifiable Inference and Privacy Preserving ML
- Compression, Optimization and a -bit- Inference Quantization
- Reinforcement learning with human feedback
- Agentic Development at scale
I am always looking to connect with people and discuss collaborations, that is the root how knowledge form and transfer, Let's have a chat!
Featured Projects
Inference Labs - Verifiable AI & LLMs
- Verifiable AI Agent - Developed the first Verifiable AI Agent by reducing overhead from 1000x to 8x
- Model-Agnostic Proof System - Designed a scalable proof of inference system leveraging Agentic testing and Probabilistic proofs with no computational overhead using JIT Design pattern and Redis Caching system.
- LLM Optimization - Led model optimization initiatives for faster inference and smaller footprint models
- RLHF-Based Ranking - Implemented sophisticated ranking profiles using Reinforcement Learning with Human Feedback (RLHF) and Group Relative Policy Optimization (GRPO)
Nobitex - Data Science & Finance
- Customer Clustering at Scale - Developed scalable, ensemble tree-based algorithm leveraging Spark for processing 4M+ customer transactions, driving MAU growth to 8.5M within one year
- Chain Fraud Detection Dashboard - Developed the Fraud pipeline discovery and classification in OTLP wallet transactions based on blockchain transaction monitoring
- Marketing Data Pipeline - Led cross-team collaboration to design an end-to-end Marketing Data Modeling ETL Pipeline with ERD system design
SnappMarket - Retail Tech & Optimization
- Autonomous Inventory System - Developed scalable inventory reordering system for 15 hypermarkets with +8,000 SKUs
- Automated Shopping Experience - Contributed to a $100M funded project for a fully automated shopping experience (Low-Cost Amazon Go), implementing indoor location tracking in collaboration with Rocket Internet
- Operational Analytics - Established real-time operational KPIs with automated reporting systems, ensuring data accuracy and driving strategic decisions
Skills
Education
M.Sc. Computer Science
- Thesis: Multi-Objective Network Weight Optimization through Hierarchical Reinforcement Learning Strategy.
- Member of Degroote finance and investment council (DFIC Club) - Quantitative Finance Department.
- Completed the Vector Institute Deep Learning and Reinforcement Learning Summer School.
> KNOW MORE
About Me
I enjoy 📰 Tech News, 📈 Business Review, 🎬 Movies, ♟️ Chess, 🎨 Pottery, 🥾 Hiking, 🔗 Blockchain technology, 👥 Meeting new people and 🌎 experiencing new cultures!
news
| Mar 19, 2025 | Our paper titled “Enhanced Pareto Optimality with Reinforcement Learning Approach” has been accepted for presentation at the CORS 2025 Conference. |
|---|---|
| Dec 20, 2024 | I successfully defended my Master’s thesis at McMaster University, focusing on “Multi-Objective Bi-Level Hierarchical Reinforcement Learning.” This work enhances traditional stochastic optimization and multi-armed bandit approaches to offer interpretable decision-making frameworks. |
| Jul 01, 2024 | I participated in the Deep Learning and Reinforcement Learning (DLRL) 2024 summer school at Vector Institute. |
| Apr 01, 2024 | I have started my Full-time position at Inference Labs to work on Verifiable Inference. |
| Sep 01, 2022 | I was accepted to McMaster University under the supervision of Prof. Manish Verma with an Excellence Scholarship. |
latest posts
| Jul 10, 2024 | Can We Verify Every Action of an AI Agent? |
|---|