Data scientist with a PhD in Operations Management and experience in causal inference, behavioral experimentation, applied machine learning, and human-AI decision systems.
About
Data scientist with a PhD in Operations Management and experience in causal inference, behavioral experimentation, applied machine learning, and human-AI decision systems. Built multi-agent LLM and RAG applications and ran randomized experiments with 1,232 participants, turning technical findings into practical decision support.
Haskayne School of Business, University of Calgary
Sep 2025–Present
Teach Business Analytics, Predictive Analytics, and Logistics Management across three teaching terms: Fall 2023, Fall 2025, and Fall 2026.
Taught 250+ undergraduates across 5 sections through Fall 2025; earned ratings of 5/5 and 7/7 and was runner-up for the 2025 Outstanding Achievement in Teaching Award.
Doctoral Researcher
Haskayne School of Business, University of Calgary
Sep 2020–Jun 2026
Designed and ran two randomized ML-fairness experiments with 1,232 participants; built the oTree and Heroku stack and analyzed outcomes with regression and Wald chi-square tests.
Developed Bayesian and rational-inattention models of human-AI decisions, deriving conditions under which error-rate disclosure improves accuracy and demographic fairness.
Projects
CrewAnalyst
A 7-agent data-analysis pipeline built on CrewAI. Upload a CSV, get back a markdown and PDF 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, visualizer, synthesizer, reporter) that converts an uploaded CSV into a polished markdown and PDF analysis report with descriptive statistics, anomaly flags, correlation insights, charts, and an executive narrative.
Engineered parallel async execution via CrewAI's async_execution task flag for 3 independent analytics agents (statistician, anomaly, correlation), cutting analysis time before the visualization step. Used Pydantic-typed schema contracts as explicit handoff interfaces between agents, and model-tier routing (Haiku for structural/classification tasks, Sonnet for reasoning and synthesis) for cost-latency tradeoffs.
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.
A LaTeX-aware RAG pipeline over structured academic papers. Uses cleaned .tex sources, section-aware chunking, FAISS embeddings, and metadata-filtered retrieval — extended with naive vs. advanced RAG comparisons, an LLM router for query-specific retrieval strategies, and a LaTeX parser for equations, headers, and appendices.
Built a RAG pipeline over structured LaTeX academic papers using section-aware chunking, hybrid FAISS + BM25 retrieval, MMR reranking, and metadata-filtered search.
Implemented an LLM router that selects between naive and advanced retrieval strategies based on query type, and built a LaTeX parser to cleanly extract equations, section headers, and appendix content.
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
PhD, Operations Management
University of Calgary
2020–Jun 2026
MSc, Industrial Engineering
Sharif University of Technology
2018–2020
BSc, Industrial Engineering
Kharazmi University
2014–2018
Awards
Paramount Resources Ltd Graduate Scholarship in Business, University of Calgary, 2024 and 2025.