Education
University of Pennsylvania
M.S.E. in Computational Science & Engineering (Scientific Computing)
Expected Graduation: 2027
- Focus areas: Machine Learning, Scientific Computing, Optimization, Stochastic Processes
- Relevant coursework: Machine Learning, Computer Vision, Stochastic Processes, Big Data Analytics, Atomistic Modeling, Advanced Topics in ML
- Teaching Assistant: Mathematical Foundation for Machine Learning II: Linear Algebra
- Affiliation: Penn Institute for Computational Science
Indian Institute of Technology, Indore
B.Tech in Metallurgical Engineering and Materials Science
Graduated: 2024
- Thesis: Graph Neural Networks for Accelerated Materials Discovery
- Strong foundation in mathematics, materials science, and computational modeling
Work Experience
Pickle — AI Engineering & Data Science Intern
Jun 2026 – Present
New York, USA
- Building recommendation, retrieval, and ranking workflows using Python and SQL to improve product discovery and personalization
- Analyzing user behavior, cohort segments, clicks, orders, and engagement signals to evaluate recommendation quality and rollout decisions
- Developing analytics pipelines and dashboards to track product performance, conversion patterns, and personalization opportunities across marketplace sessions
Research Assistant – Agentic LLM Text Scoring
Jan 2026 – Present
World Well Being Project, UPenn (Prof. Lyle Ungar) — Philadelphia, USA
- Designing scalable agentic AI pipeline with LangGraph and Python to score 150K+ messages with automated QA validation and logging checks
- Applied BERTopic clustering and embedding-based modeling to detect user patterns across cohorts and improve scoring results by 11% overall
- Building reproducible ML workflows with experiment tracking and modular, automated evaluation frameworks for rapid iteration and audits
Deloitte USI — Analyst, AI & Data Analytics
Aug 2024 – Aug 2025
Hyderabad, India
- Led a real-time AI-based liver disease prediction project using Python and Streamlit to enhance early detection and outcomes
- Built probabilistic, statistical, and optimization models using PySpark, SQL, and Azure for inventory and supply-chain optimization
- Delivered 100M USD+ in operational impact for U.S. Fortune 500 clients through data and model-driven decision-making
- Automated data pipelines and storytelling dashboards in Power BI to deliver insights and drive strategic business decisions
Aalto University, Finland — Research Intern (Machine Learning)
Summer 2024
Espoo, Finland
- Developed a hybrid data-physics and AI model for hydrogen-tolerant metals, targeting runtime improvement by 15%
- Scaled microstructural simulations across 200+ metal elements on CSC HPC clusters using Slurm for parallel execution
- Built and trained temporal Graph Neural Networks to predict dynamic stress-strain behavior from microstructural graphs
INRS, Canada — Mitacs Globalink Research Intern
Summer 2023
Montreal, Canada
- Generated data through advanced computational techniques and DFT for designing materials for sustainable energy applications
- Modeled 300+ materials using Graph Neural Networks and PyTorch Geometric to predict carbon dioxide adsorption
- Developed a Python and VASP-based graph augmentation method with intermediate structures, improving model accuracy 5X
Projects
AI Agent for Sprint Intelligence - YHack'26
Built an AI-powered Slack-to-Jira system that classified threads, auto-generated sprint tickets, mapped expertise from GitHub PR history, and surfaced team workload through a full-stack analytics dashboard.
Safety-Aware Multi-Agent RL for Coordination in MiniGrid
Built a safety-aware multi-agent RL system in MiniGrid using MAPPO and Lagrangian constraints, improving coordination efficiency and task success while reducing safety violations.
Smart Vision Based Bin Monitoring System
Built a real-time CV pipeline for trash detection, tracking, and classification using ROI filtering, ByteTrack, and YOLO pose-based hand removal.
Cloudphysician - Vital Extraction using CV
Developed a fast CV-OCR system for automated vital extraction from ECG images, delivering 96% accuracy and sub-second CPU inference to support clinical decision-making.
RADAR – Personal Research Recommendation Agent
Built an agentic research assistant that reads recent notes, infers active topics, retrieves relevant papers from arXiv and Semantic Scholar, and ranks personalized recommendations with memory.
Graph Neural Networks for Accelerated Materials Discovery
Accelerated crystal structure relaxation using GNNs, delivering DFT-comparable energies with 2.51% error for 300+ materials in seconds across 70+ alloys.
About
I am an MSE student in Computational Science at the University of Pennsylvania with a strong foundation in machine learning, data science, scientific computing, and optimization. My work spans recommendation systems, retrieval and ranking workflows, graph neural networks, computer vision systems, and large-scale optimization and analytics in industry. I enjoy solving complex, high-impact problems and translating them into efficient models, algorithms, pipelines, and decision-support systems.
- Skills: Python, PyTorch, SQL, ML, DL, CV, GNNs, Optimization, Recommendation Systems, Retrieval, Ranking
- Focus: Machine Learning, Data Science, Recommendation Systems, Computer Vision, Graph Neural Networks, Statistical Modeling
- Currently: AI Engineering & Data Science Intern at Pickle; seeking internships in Machine Learning, Data Science, and Computational Science
Contact
Email me at kotian2@engineering.upenn.edu or DM me on LinkedIn.