공급사 목록 불러오는 중… · Loading suppliers…
RL ENVIRONMENT SOURCING FOR AI LABS
Narrow by domain and environment. Compare suppliers.
Write your requirements once. Draft a request for each supplier.
Verifiable environments for cybersecurity, SRE, compilation and STEM reasoning.
5 listed itemsMykyta Mudryi, Markiian Chaklosh
Founder: security consulting at Leviathan Security Group
Company size 11–50Long-horizon coding, computer use, professional work and autonomous research environments.
4 listed itemsAarush Kukreja, Ayush Karupakula
Aarush Kukreja: Princeton CS · SWE-bench Verified / SWE-agent research at PLI · MIT·Caltech research (per his own bio)
Company size 1–10Computer-use environments with task and verification artifacts across desktop applications and cross-app workflows.
6 listed itemsFrancesco Bonacci, Dillon DuPont
Microsoft Windows Agent Arena research and engineering background
Company size 1–10Privately built tasks compatible with Terminal-Bench and SWE-bench formats; independent of those benchmarks.
3 listed itemsShahzaib Awan, Shehryar Awan
Company size 51–200Expert-built RL environments across technical and professional work.
1 listed itemGarrett Lord, Ben Christensen, Scott Ringwelski
MIT-PhD research/engineering team joined via the Cleanlab acquisition
Company size 500+Realm combines domain experts with RL environment development.
1 listed itemAli Ansari
Chief Economist Mark Esposito: policy researcher affiliated with Harvard Berkman Klein Center and Kennedy School CID; AI-venture co-founder
Company size 51–200AI training data and evals for hardware-design domains (aerospace, robotics, semiconductors, medical devices).
1 listed itemAnson Yu, Hudhayfa Nazoordeen
Waterloo · experience at Notion, Fuse, Cohere, Xanadu
Company size 1–10Long-horizon environments for measurable science, robotics and security outcomes.
1 listed itemSarah Helmbrecht, Dakotah Martinez
Sarah Helmbrecht: NYU Courant math MS · Dakotah Martinez: physics PhD (theoretical physics, HPC)
Company size Not disclosedSimulated software, finance and research workflows for agent training.
2 listed itemsAnand Kannappan, Rebecca Qian
Meta AI and Meta Reality Labs research background
Company size 11–50Long-horizon engineering and research tasks with verifiers; creator of FrontierSWE.
2 listed itemsCalvin Chen, Justus Mattern, Navid Pour
Research/engineering team from Cursor, Prime Intellect RL and Jane Street
Company size 11–50Off-the-shelf RL environments for repository coding, terminal work, tool use and long-horizon professional tasks.
4 listed itemsEdwin Chen
Google·Facebook·Twitter ML · MIT math and linguistics
Company size 51–200Post-training datasets and private evals across STEM, enterprise domains, audio, multimodality and robotics.
6 listed itemsKrishay Mukhija, Pranay Manocha, Akash Jain
Company size 11–50Browser, desktop and MCP tool environments for long-horizon software, enterprise and STEM workflows, with a dedicated sample request form.
1 listed itemJonathan Siddharth, Vijay Krishnan
Leadership from Meta, Google, Microsoft, Apple, Amazon, Stanford, Caltech, MIT
Company size 201–500Research, reasoning and software tasks derived from named benchmark formats.
19 listed itemsPrzemek Chojecki
Research team of PhD-level mathematicians and engineers
Company size 1–10Expert-designed interactive RL tasks and verifiers for complex domains.
2 listed itemsJosé André Nunes, Alexandre Bernat, Gabriel Albuquerque, Rodrigo Schmidt
Rodrigo Schmidt: 30+ years of engineering leadership, incl. 15 at Meta
Company size 1–10Suppliers that build or supply RL environments and tasks. Public benchmarks are separate from commercial offerings. Confirm scope, prices and sample access with each supplier.