RL Environment Engineer

RL ENVIRONMENT ENGINEER Blockhouse, full time, NYC in person or hybrid preferred, remote within US time zones considered ABOUT BLOCKHOUSE Blockhouse gives institutional asset managers access to the kind of trading infrastructure that usually takes years and millions of dollars to build. Founded in 2022, we run a noncustodial platform where clients keep custody of their assets while they trade, hedge and compound portfolios across crypto and tokenized markets, from FX and equities to treasuries and compute futures. Alongside the platform we run live delta neutral funding rate and market making strategies with client capital across major venues, and we keep expanding into new frontier markets such as compute hedging. THE ROLE We're turning the research and engineering work behind our live trading into reinforcement learning environments that frontier AI labs can use to train and evaluate agents on real quantitative work. You'll build that environment hands on, from mining hard tasks out of our team's actual research and systems work to the sandbox, graders and harness that make those tasks reproducible for a lab. You'll work directly with the founders and our quant team, and we care far more about what you've built than how many years you've been working. This isn't a speculative bet. We already work with frontier labs and have closed a high six figure AI training partnership built on our own in house research, and environments are our natural next step, so the tasks you build go straight into an active sales pipeline. WHAT YOU'LL DO

• Build long horizon environments for quant research and trading systems engineering, chaining stages from data curation and feature work through backtesting and deployment
• Turn real research mistakes and engineering incidents from our team into well specified tasks with clear, verifiable grading
• Design graders and reward signals that hold up for both deterministic and open ended outputs
• Run frontier models through the tasks with evaluation harnesses such as Harbor, and turn the results into benchmarks we can share with labs
• Help shape the sandboxing and data packaging standards labs expect WHAT WE'RE LOOKING FOR
• You've built an RL environment, eval suite, benchmark or agent harness for LLMs before, whether at a company, in research, in a hackathon or as a side project
• Strong Python, with good habits around testing and reproducibility
• Comfort with containers, cloud compute and running many agent runs at scale
• Curiosity about markets and quant research, though no trading background is required
• Recent grads and early career engineers are very welcome to apply NICE TO HAVE
• Experience in LLM post training, RLHF or reward modeling
• Exposure to quantitative research, backtesting or market data
• Familiarity with tools like Harbor, Inspect or SWE bench style harnesses WHY BLOCKHOUSE
• Ownership of a new product line from the first version
• Close work with the founders and our quant team
• Significant upside tied directly to what you build
• Real, hard problems drawn from a live trading business COMPENSATION Base salary of $60,000 to $84,000, plus a significant percentage of revenue from every sale of the environments and tasks you help build, which we expect to make up most of your total compensation. Total compensation for strong performers is expected to well exceed base.