You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Combinatorial Decision Making and Optimization project on Very Large Scale Integration (VLSI) with Constraint Programming (CP), propositional SATisfiability (SAT), and Satisfiability Modulo Theories (SMT)
Develop optimal solutions to a scheduling problem by modelling it as a Constraint Satisfaction Problem (CSP), a method used widely in the field of Artificial Intelligence.
A smart duty scheduling application built with Streamlit and Google OR-Tools. Features automated roster optimization, multi-team support, fairness balancing, and configurable constraints.
What if ethics were part of the math? MAAT-Core is a Python library where safety is a hard constraint and optimization respects boundaries by design. A minimal framework for ethical AI, complex systems, and reproducible research.
AI-powered production scheduling with constraint satisfaction — optimizes across machines, materials, labor, and orders to maximize throughput and minimize tardiness
Plan trips around live events: track artist/comedy/sports tour dates via Bandsintown, map them, and organise no-payment group trips. Single-file Streamlit prototype - a preference-weighted optimiser and its eval are roadmap, not yet built.
I've open-sourced Delegator v5.2.1: a state-based AI scheduler designed for large-scale public park maintenance planning in Japan. It converts playground inspection scores into actionable repair/update schedules under budget and workforce constraints — all in under 2 seconds across 1,300+ units. Scalable. Transparent. Real.
Daily-fantasy-sports lineup optimizer: Google OR-Tools constraint optimization builds salary-cap lineups, then an Anthropic Claude reasoning layer explains, rates, and suggests swaps. Includes real-time data ingestion and portfolio/exposure management.
MotoGP season calendar optimisation using simulated annealing, genetic algorithms, and particle swarm optimization minimizing travel distance under temperature and summer-break constraints.