Hey there! I'm Kushagra Bharti
I am a student and software builder who enjoys learning and expanding my skillset.
{ values / beliefs / writings / thoughts }
epistemic velocity
Lifelong learning as epistemic hygiene: curiosity, discipline, and pressure against stale competence.
adaptive agency
High-agency adaptation under ambiguity: fast revision, clear authorship, tools kept subordinate.
aesthetic judgment
Taste as compressed perception: rhythm, restraint, framing, and selection when generation is cheap.
ambient agency
Software as ambient infrastructure: fewer destinations, stronger memory, cleaner preservation of intent.
25.2048° N, 55.2708° E+
Exploring the frontier of tech: agents, algorithms, and machine learning.
Places, teams, and problems that shaped how I build.
Feb 2026 - Present
Research
Fine-tuning DeepLabCut/SuperAnimal for lab-specific 3-chamber mouse-behavior video and building an end-to-end computer vision pipeline for pose extraction, behavioral scoring, QC, and researcher-facing scorecards.
Apr 2025 - Present
Research
Built MonopolyBench, a deterministic multi-agent LLM benchmark for evaluating tool-calling agents on long-horizon planning, negotiation, deception, bias, memory, and schema-constrained decision-making.
Jan 2026 - May 2026
Industry
Led engineering for Glydr.gg's Railway-deployed, microservice-based configuration platform serving 1,000+ users, spanning public discovery, Steam authentication, admin tooling, Control Panel imports, CI/CD, and distributed config delivery.
Apr 2025 - Nov 2025
Research
Built paper-faithful optimization solvers and a solver-labeled dataset pipeline for 1D drone coverage planning, with benchmarks and QC gates to support supervised, GNN, and RL experiments on optimal tour planning.
May 2024 - Aug 2024
Industry
Owned Llama 3.1 fine-tuning, structured-output engineering, cost optimization, telemetry, and latency work for Abilitie AI Cases, reducing LLM cost per conversation 70% across 27 role-play configurations and reaching 1.0s p95 TTFT.
Aug 2021 - May 2022
Leadership
Supported younger boarding students through peer mentorship, safety training, and community-building in a residential school environment.
A deterministic long-horizon LLM-agent benchmark for evaluating planning, negotiation, deception, memory, bias, and asset-management behavior.
A custom Gymnasium Monza RL environment and PPO training stack with F1-style physics, ray-cast perception, telemetry calibration, and replay.
A top-6%-worldwide IMC Prosperity 4 trading system spanning fair-value market making, options pricing, residual signals, DP oracles, and replay diagnostics.
A hackathon winner mobile accountability app where users turn goals into escrow-backed commitments, submit proof, and rely on trusted validators.
A high-concurrency Go web crawler with worker pools, host-aware frontier scheduling, PostgreSQL persistence, and 100,000-page public-web crawl runs.
A live multi-stage LLM benchmark where frontier models generate, critique, revise, and vote on creative prompts under pressure.
A geometry-first computer vision system for automatic lens correction, combining a staged ResNet34 hybrid CNN with Brown-Conrady camera geometry.
An artifact-first AI workspace with specialized studios, tool-calling runs, durable context, model comparison, and storage-backed outputs.
A complete Titanic ML pipeline covering data cleaning, feature engineering, model comparison, EDA, and a documented learning report.
2022 / documentary / 10 min
A documentary following the St. Stephen's dining hall staff from the start of their day to the end.
Open to internships, research collaborations, and ambitious builds.