{ values / beliefs / writings / thoughts }
perpetual learning
Remaining deliberately unfinished before competence becomes a room with no other door.
kinetic agency
Ruining the perfection of the unattempted by putting work into contact with reality.
discernment
Selection as a creative act: what to keep, automate, complicate, and leave outside.
predictions
Three notes on vanishing interfaces, affordable failure, and freedom in an over-helpful world.
Places, teams, and problems that shaped how I build.
Jul 2026 - Aug 2026
Industry
Architected and launched Corgi's first commercial insurance broker platform, unifying onboarding, underwriting, payments, servicing, and commissions to open a new revenue channel. Built a production AI agent combining company knowledge, persistent memory, and custom tools for broker and sales automation.
Nov 2025 - Present
Research
Created MonopolyBench to study how LLM agents plan, negotiate, and behave over long horizons. Built the simulation, agent harnesses, and evaluation infrastructure to diagnose capabilities, failures, and alignment risks through reproducible experiments.
Jan 2026 - May 2026
Industry
Built and launched Glydr's community marketplace for gaming and productivity keybind profiles. Engineered the full stack, immutable versioning, and secure desktop imports to connect profile discovery and publishing with the company's foot controllers. This was done through Consult your Community.
Feb 2026 - Jun 2026
Research
Built a computer vision pipeline for behavioral neuroscience, from model fine-tuning to validated behavior scoring. Turned noisy lab footage into stable pose tracks, interpretable measurements, and reproducible research outputs with explicit quality controls.
Jan 2026 - Jul 2026
Supported UT Dallas residential life through student guidance, crisis response, conflict resolution, and community programming.
Apr 2025 - Nov 2025
Built exact optimization solvers and a research data pipeline for learning drone coverage plans, producing verified training targets and controlled tests of generalization.
May 2024 - Aug 2024
Industry
Delivered full-stack systems for Abilitie AI Cases, bringing enterprise role-play training from model responses into an interactive product. Led open-source model fine-tuning and engineered the inference, observability, and response-generation systems behind its quality, speed, and cost improvements.
Aug 2021 - May 2022
Supported a boarding-school community through peer mentorship, residential leadership, conflict resolution, and emergency preparedness.
Software (and some hardware) I have designed, built, and shipped.
A research benchmark for long-horizon LLM agency in a persistent economy. Combines multi-agent simulation, controlled experiments, and auditable trajectories to diagnose strategic reasoning, negotiation, tool-use failures, and alignment risks as decisions compound over time.
A telemetry-calibrated Formula 1 physics simulator and GPU-accelerated learning system. Combines evolutionary controller search, behavior cloning, and reinforcement learning to develop racing policies, with CPU-verified trajectories and deterministic replay connecting simulation, training, and evaluation.
Placed top 6% worldwide among 18,803 teams in IMC Prosperity 4. Built market-making, options-pricing, and statistical-arbitrage strategies alongside a Rust/Python research system for fast backtesting, execution analysis, and validation across changing market regimes.
A shared workspace for agents that research, execute, and deliver work using company knowledge. Combines durable orchestration, isolated code execution, persistent memory, and human approvals so teams can recover runs, review outputs, and automate repeatable workflows.
A high-throughput Go crawler combining breadth-first discovery with fair host scheduling, bounded concurrency, and fault isolation. Sustained roughly 147 pages per second on the public web while streaming extracted content and discovery paths into a live reading interface.
Won 1st place in HackSMU's Solana Track with a mobile platform that turns commitments into financial stakes. Engineered peer validation, server-enforced lifecycle transitions, and token escrow to connect proof, majority voting, and settlement.
A digital museum of my engineering, research, writing, and film, paired with a private system for running my daily work. Combines calendar synchronization, durable task workflows, and an OAuth-secured MCP server that lets AI assistants act within explicit permissions.
A live research arena for evaluating how frontier models generate, critique, and improve creative ideas. Orchestrates anonymous multi-model review and judging, combining durable execution, Glicko ratings, and bias audits to make creativity evaluation inspectable and statistically qualified.
A neural lens-correction system that combines analytic camera geometry with learned residual flow. Engineered differentiable warping, staged GPU training, and geometric safety checks to preserve image structure, earning an honorable mention in the AutoHDR competition.
Stories and taste make us human, and I enjoy telling them through the lens.
reel
2022 / documentary
screen reel10:00
reel
2023 / documentary
screen reel19:00
reel
2018 / recap
screen reel03:00
for fastest response
Kushagra Bharti