About
I’m an operations and behavioral researcher working at the intersection of algorithmic fairness, human-AI decision-making, and behavioral experimentation. I completed my PhD at the University of Calgary’s Haskayne School of Business, where my research used large randomized experiments and formal analytical models to understand when AI helps people decide well — and when it quietly steers them wrong.
Alongside the research, I build things. Recently that’s meant multi-agent LLM systems, experimentation infrastructure, and teaching materials for 250+ undergraduates. I’m focused on applied ML, data science, responsible AI, and operations research roles where rigorous causal, analytical, and engineering skills can improve real-world data and product decisions.
Technical Skills
- Languages & Tools
- Python, R, SQL, LaTeX, Git, Excel (advanced modeling), ArcGIS.
- ML & Statistics
- scikit-learn, TensorFlow, logistic / OLS / Poisson regression, causal inference (A/B testing, instrumental variables, difference-in-differences), hypothesis testing, experimental design, cross-validation, feature engineering.
- Agentic AI & LLMs
- OpenAI Agents SDK, CrewAI, Pydantic structured outputs, multi-agent orchestration with typed schema contracts. Familiar with LangChain and MCP.
- Engineering & Research Infrastructure
- FastAPI, PostgreSQL, React, Gradio, Heroku, uv, oTree, Prolific.
Selected Projects
AutoAnalyst
A 7-agent data-analysis pipeline built on CrewAI. Upload a CSV, get back a structured HTML report with statistics, anomalies, correlations, visualizations, and an executive narrative. Parallel async execution, Pydantic-typed schema contracts between agents, and model-tier routing for cost-latency tradeoffs.
- Architected a 7-agent pipeline (profiler, statistician, anomaly, correlation, viz, synthesizer, reporter) that converts an uploaded CSV into a polished HTML analysis report with summary statistics, anomalies, correlations, charts, and an executive narrative.
- Engineered parallel async execution (asyncio.gather) for 3 independent analytics agents, Pydantic-typed schema contracts between agents as explicit handoff interfaces, and model-tier routing (Haiku for structural tasks, Sonnet for reasoning) for cost-latency tradeoffs.
GitHub repoDude
A 3-agent natural-language interface (OpenAI Agents SDK) for a budgeting app. Translates plain-English questions about spending into structured retrieval and analytics over transaction data. Deployed in a FastAPI / PostgreSQL / React app in daily production use.
- Built a 3-agent system (conversational, retrieval, analyst) that translates plain-English budgeting questions into structured retrieval plus analytics over transaction data.
- Deployed into a FastAPI / PostgreSQL / React app in daily production use, integrated via Claude Code from an isolated mock-data prototype to the live database.
GitHub repoResearch
Shaping Programmer Practices: Mitigating Bias in ML Development.
Designed and ran two randomized behavioral experiments (N=604 and N=628; 1,232 participants total) simulating an end-to-end ML hiring-model pipeline under varied fairness and accountability interventions. Reject & Resubmit, Production and Operations Management Journal.
- Built the full experimental stack: interface in oTree, deployment on Heroku, recruitment via Prolific, analysis with logistic regression, Wald chi-square tests, and exploratory text analysis.
- Found fairness-norm messaging nearly doubled the odds of submitting the fairest model (OR approx. 2.0); high accuracy targets raised the odds of submitting the least fair model (OR up to 1.71); the combined norm + accountability intervention showed a negative interaction (OR=0.43), revealing non-additive effects with direct governance implications.
Collaborative Fairness: Human and Machine Interaction.
Developed a formal Bayesian + rational-inattention model of human-AI decision-making; proved threshold conditions under which disclosing group-specific AI error rates improves both aggregate accuracy and demographic fairness. Working paper. Presented at MSOM, CORS, and AIMOR 2025.
- Identified a non-obvious failure mode in which awareness can reverse disparity direction under specific parameter regions, showing why aggregate accuracy audits can mask group-level harm.
Education
Ph.D. in Operations and Supply Chain Management
University of Calgary, Haskayne School of Business · Calgary, AB
- Dissertation: Toward Fair AI Systems: Programmer Practices, Human-Machine Bias, and Trust Dynamics.
- Advisors: Osman Alp, Justin Weinhardt, Alireza Sabouri.
M.Sc. in Industrial Engineering
Sharif University of Technology · Tehran, Iran
- Thesis: Predicted next-day market direction from Twitter and news-headline sentiment. Designed a credibility-filtered influencer identification step, engineered sentiment features, and trained scikit-learn classifiers plus a TensorFlow feedforward neural network. Lifted binary-classification accuracy from 51% (chance) to 67%.
B.Sc. in Industrial Engineering
Kharazmi University · Tehran, Iran
Teaching & Leadership
Instructor, Haskayne School of Business, University of Calgary
MGST 391 Business Analytics (4 sections) and SCMA 455 Logistics Management (1 section)
- Independently taught 250+ undergraduates across 5 sections. Student ratings: 5/5 most recent and 7/7 earlier terms. Runner-up, Outstanding Achievement in Teaching Award (2025).
- Translated the technical OR toolkit (optimization, simulation, forecasting, queuing, decision analysis) into applied managerial decision frameworks; designed 12 hands-on logistics activities spanning routing, facility location, and transportation planning.
- Designed Morning Dash, an interactive TSP/VRP classroom competition that turned abstract heuristics and computational-complexity concepts into a live, incentivized experience for students.
Awards & Service
- Paramount Resources Ltd Graduate Scholarship in Business, University of Calgary (2024, 2025).
- Runner-up, Outstanding Achievement in Teaching Award, University of Calgary (2025).
- Treasurer & Board Member, Alberta Student Chapter of the Canadian Operational Research Society (2024-2025); Session Chair, CORS Annual Conference (2024).