Joshua Barre

Reinforcement learning for dual-arm robotic cloth folding. I started by working out why no policy was learning the task, and found three independent reasons: the goal encoded a 180° rotation of a flat sheet rather than a fold, so folding the cloth actually made the score go down; the target corner sat about 8 cm outside the arm's reachable workspace, which I established by sampling 40,000 joint configurations per arm and running forward kinematics; and the environment's IK solver stalled 0.104 m away from solutions that provably existed. I rebuilt it as a reachable edge fold and trained the pipeline end to end — a scripted expert with damped least-squares IK, behavior cloning to 83%, then PPO fine-tuning — reaching 100% fold success, against 0% for PPO trained from scratch. It ships as a wrapper that leaves the shared environment untouched, with committed checkpoints and pinned solver versions so it runs straight from a clone.

Led a team of 4 engineers building the AI outreach agents for a B2B platform serving non-profits, replacing manual calling and data entry. I scoped and assigned the work, trained the team on the stack, and reviewed everything they shipped. I built an LLM-powered SMS agent that holds two-way conversations and parses replies into structured records, and a voice agent that autonomously places calls, transcribes them, and feeds the same extraction pipeline. Running campaigns across every Canadian province produced a dataset of 1,200+ entries, and I built the cleaning and analysis workflows that turned raw conversation data into reporting the team could act on.

Built and deployed neural network models to estimate material reliability under stress, with automated scoring replacing manual review. Streamlined Python and Azure AI evaluation pipelines for an 83% runtime reduction, owning the end-to-end loop from data preparation through training, evaluation, and monitoring. Shipped model updates, testing workflows, and reliability dashboards with a U.S.-based team, documenting model behaviour and edge cases so results reproduced consistently across runs.