Mehdi is available for hire
Hire MehdiMehdi Ghasemi
Verified Expert in Engineering
Optimization Developer
Edmonton, AB, Canada
Toptal member since July 4, 2019
Bio
Mehdi is a PhD-level mathematician and senior data scientist with 7+ years of experience delivering production ML systems for the public sector. At the Edmonton Police Service, he leads AI/ML strategy, including predictive analytics and privacy-preserving ML pipelines. Previously, he deployed a recidivism-risk model for Saskatchewan correctional facilities. His work spans statistical modeling, optimization, RAG/agentic systems, and MLOps.
Portfolio
Edmonton Police Service
Bayesian Inference & Modeling, Data Visualization, Jupyter, Python, SQL...
University of Saskatchewan
Statistics, Mathematics, Python, Mentorship & Coaching, Applied Research...
Government
SQL, Python, Pandas, Keras, Time Series Analysis, Statistics, Scheduling, Flask...
Experience
- Mathematical Modeling - 12 years
- Optimization - 12 years
- APIs - 10 years
- Applied Mathematics - 10 years
- Machine Learning - 10 years
- Scikit-learn - 8 years
- Demand Forecasting - 6 years
- Natural Language Processing (NLP) - 4 years
Work Experience
Senior Scientist | Mathematician
2020 - PRESENT
Edmonton Police Service
- Analyzed and extracted information from historical documents so that the unstructured data becomes semi-structured and digestible by AI algorithms. This task involved image processing, NLP, LLM, and mathematical optimization.
- Made adjustments to police communication branch staffing to meet and improve upon national minimum standards.
- Forecasted the impact of COVID-19 on the police force and its corresponding risk analysis.
- Analyzed the transition of heavy drug users over time. Also, studied the network of drug users and distributors around the city and effective methods for concentrated disruption of drug-related offenses.
Technologies: Bayesian Inference & Modeling, Data Visualization, Jupyter, Python, SQL, Scheduling, Stochastic Modeling, Machine Learning, Trend Analysis, Forecasting, Mathematical Modeling, Natural Language Processing (NLP), Image Processing, Optimization, Computational Geometry, Pandas, Keras, OpenCV, Mathematics, Time Series Analysis, Statistics, Web Programming, Flask, Model View Controller (MVC), Visualization, Databricks, Large Language Models (LLMs), OpenAI, Artificial Intelligence (AI), Data Analysis, Data Analytics, Data Scientist, Data Modeling, Data Science, Logistic Regression, Statistical Modeling, Consulting, Technical Leadership, Time Series, Data Manipulation, Generative Pre-trained Transformers (GPT), Modeling, Generative Artificial Intelligence (GenAI), Applied Research, Fine-tuning, Conda, Computer Vision, Web Development, Agentic AI, Webhooks, Retrieval-augmented Generation (RAG), Agentic AI Systems, XGBoost, Linear Regression, Model Deployment, Data Pipelines, Time Series Forecasting, Demand Forecasting, Model Development, Model Evaluation, Feature Engineering, Data Engineering, Solution Architecture, Data Architecture, Stakeholder Management, APIs, Algorithms, Applied Mathematics, MySQL, Scikit-learn, Agile Project Management, Deep Learning, Machine Learning Operations (MLOps)
Adjunct Professor
2018 - PRESENT
University of Saskatchewan
- Collaborated with other researchers in scientific projects that involve mathematical modeling.
- Co-supervised graduate students in areas related to optimization and computer science.
- Provided scientific consultation to identify, solve, and implement solutions to industrial problems.
Technologies: Statistics, Mathematics, Python, Mentorship & Coaching, Applied Research, Communication, Algorithms, Applied Mathematics, Scikit-learn, Agile Project Management
Data Scientist
2017 - 2020
Government
- Designed and implemented pipelines to extract specialized datasets out of the administrative database.
- Used government data and analyzed some of the existing practices to find bottlenecks and optimized procedures.
- Employed machine learning to improve decisions made based on standard assessments.
- Evaluated the feasibility of new policies to achieve certain goals by employing time-series analysis and forecasting.
- Made a local and provincial evaluation of initiatives in correction, justice, and child welfare.
Technologies: SQL, Python, Pandas, Keras, Time Series Analysis, Statistics, Scheduling, Flask, Model View Controller (MVC), Visualization, Machine Learning, Artificial Intelligence (AI), Data Analysis, Data Analytics, Data Scientist, Data Modeling, Data Science, Logistic Regression, Statistical Modeling, Time Series, Data Manipulation, Modeling, Applied Research, Fine-tuning, Conda, Web Development, XGBoost, Linear Regression, Model Deployment, Data Pipelines, Time Series Forecasting, Demand Forecasting, Model Development, Model Evaluation, Feature Engineering, Data Engineering, Data Architecture, Stakeholder Management, APIs, Algorithms, Applied Mathematics, MySQL, PHP, Scikit-learn, Bayesian Inference & Modeling, Machine Learning Operations (MLOps)
Consultant
2017 - 2018
The Centre for Forensic Behavioural Science and Justice Studies
- Analyzed the risk assessment tool LSI (Level of Service Inventory).
- Applied machine learning to LSI data to obtain personalized preventive interventions for offenders.
- Organized and managed workshops to expand the professional and scientific network of the Centre.
Technologies: SQL, SPSS, Python, Pandas, Data Analytics, Data Scientist, Data Modeling, Data Science, Logistic Regression, Statistical Modeling, Consulting, Mentorship & Coaching, Data Manipulation, Modeling, XGBoost, Linear Regression, Data Pipelines, Time Series Forecasting, Model Development, Model Evaluation, Communication, Feature Engineering, Data Engineering, Algorithms, MySQL, PHP
MITACS Postdoctoral Fellow
2015 - 2017
University of Saskatchewan
- Organized the Saskatoon Police Predictive Analytics Laboratory.
- Built a mathematical simulation of the missing children phenomenon to identify its deriving factors among youth.
- Researched the optimization and moment problem in the applied context.
Technologies: Python, Optimization, Mathematical Modeling, Pandas, Web Programming, Flask, Visualization, Machine Learning, Data Analytics, Data Science, Logistic Regression, Statistical Modeling, Web Development
Postdoctoral Research Fellow
2013 - 2014
Nanyang Technological University
- Implemented semidefinite programming UI for SAGE and Python.
- Research advanced polynomial and convex optimization.
- Developed the topological moment problem using functional analysis and real algebraic geometry.
Technologies: Sage, Python, Mathematical Modeling
Project History
SKSurrogate
https://github.com/mghasemi/sksurrogateA scikit-learn-based suite for optimizing expensive black-box functions: surrogate-driven hyperparameter tuning and pipeline search (AutoML). Combines evolutionary search with Gaussian-process surrogates to explore non-convex parameter spaces; includes a custom Hilbert-space kernel regressor and accepts any scikit-learn estimator. Ships published benchmarks across six UCI datasets, live documentation on Read the Docs, and a Zenodo DOI for reproducible results.
Irene Project
https://github.com/mghasemi/IreneA Python toolkit for constrained polynomial optimization: sum-of-squares and moment semidefinite programs, sums of nonnegative circuits (SONC), and hybrid relaxations — generalizing Lasserre's hierarchy over bounded algebraic feasible sets. Based on solutions of generalized truncated moment problems over commutative real algebras, the core of my Ph.D. research, actively maintained with a Zenodo DOI and an accompanying software paper under peer review.
InventoryOptim
https://github.com/mghasemi/InventoryOptimGiven inventory data of multiple interacting commodities from stock with limited but variable capacity, provide insight on:
1. Estimating future required capacity for each item based on a particular terminal segment of data
2. Future cost estimation for each item
3. How the trends of individual items would change, assuming a trend change at given times in the future for some items
4. Given a budget limit, how should trends change to ensure a non-negative residual
1. Estimating future required capacity for each item based on a particular terminal segment of data
2. Future cost estimation for each item
3. How the trends of individual items would change, assuming a trend change at given times in the future for some items
4. Given a budget limit, how should trends change to ensure a non-negative residual
Stochastic-Scheduling — Scheduling Toolkit
https://github.com/mghasemi/Stochastic-SchedulingA Python library for modeling tasks, assigning work to resources, and comparing scheduling strategies: a dependency-free core (task model + FCFSP heuristic) plus optional Pyomo MILP models for multi-machine scheduling, stochastic strategy evaluation via simulation, Gantt-chart visualization, and synthetic-data tools. Works with GLPK, HiGHS, or CPLEX; includes an optional PCB workload case study.
RAG & Agentic AI — TinyRAG
https://github.com/mghasemi/TinyRAGA lightweight, self-hosted retrieval-augmented generation system (FastAPI, React, ChromaDB, Docker Compose): multi-format document ingestion, isolated collections, streaming QA with source citations, runtime LLM switching, and an MCP server that lets AI agents query your documents. Runs on local inference runtimes. Paired with AgentDesign — design of a local-first AI research agent that learns the operator's workflow. This is the working evidence behind the "Agentic AI / RAG Systems" chips in my profile.
pyProximation
https://github.com/mghasemi/pyProximationThis package was originally written to solve systems of integro-differential equations via the collocation method in an arbitrary number of variables. The current implementation of the method is based on a finite-dimensional orthogonal system of functions. Therefore, additional modules were required to achieve this goal.
Nonlinear Regression
https://github.com/mghasemi/nonlinear-regressionA small suite of tools to perform nonlinear regression, sci-kit-learn style. It uses linear regression and data transformation to perform unweighted nonlinear regression and implements a version of function spaces as Hilbert spaces to do weighted nonlinear regression.
Education
2009 - 2012
Ph.D. in Mathematics
University of Saskatchewan - Saskatoon, Canada
2002 - 2004
Master of Science Degree in Mathematical Logic
Tarbiat Modares University - Tehran, Iran
1998 - 2002
Bachelor of Science Degree in Mathematics
Amirkabir University of Technology - Tehran, Iran
Certifications
DECEMBER 2022 - PRESENT
Project Management Fundamentals
INEXERTUS
Skills
Libraries/APIs
Scikit-learn, Keras, Pandas, XGBoost, Sage, OpenCV
Tools
LaTeX, PyCharm, Jupyter, SPSS, Git, GitHub Copilot
Languages
Python, SQL, PHP
Frameworks
Flask
Paradigms
Model View Controller (MVC), Agile Project Management
Platforms
Linux, Databricks
Storage
MySQL, SQLite, Data Pipelines
Other
Statistics, Mathematics, Mathematical Modeling, Optimization, Machine Learning, Time Series Analysis, Artificial Intelligence (AI), Data Analysis, Data Analytics, Data Scientist, Data Modeling, Data Science, Logistic Regression, Statistical Modeling, Data Manipulation, Modeling, Linear Regression, Model Deployment, Time Series Forecasting, Model Development, Model Evaluation, Communication, Solution Architecture, Data Architecture, Machine Learning Operations (MLOps), Stakeholder Management, APIs, Algorithms, Applied Mathematics, Scheduling, Trend Analysis, Forecasting, Web Programming, Visualization, Data Visualization, Bayesian Inference & Modeling, Natural Language Processing (NLP), Computational Geometry, Deep Learning, Large Language Models (LLMs), Consulting, Mentorship & Coaching, Time Series, Generative Artificial Intelligence (GenAI), Applied Research, Fine-tuning, Image Generation, Text to Image, Conda, Web Development, Agentic AI, Webhooks, Retrieval-augmented Generation (RAG), Agentic AI Systems, Demand Forecasting, Feature Engineering, Data Engineering, Stochastic Modeling, Image Processing, Global Project Management, OpenAI, Leadership, Technical Leadership, Generative Pre-trained Transformers (GPT), Computer Vision, RAG Systems
Collaboration That Works
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
1
Share your needs
Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2
Choose your talent
Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3
Start your risk-free talent trial
Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.
Top talent is in high demand.
Start hiring