AI/ML Engineer, RL Environments - Asset Hub
$140,000–$200,000 year
On-siteNew York City, New York, United States
Job Summary
Ingest production codebases, workspaces, and databases from shut-down companies to identify high-value AI-training products like reinforcement-learning environments, agentic task suites, and fine-tuning datasets. Build pipelines transforming raw assets into derivative works through repository ingestion, commit-mining for task extraction, and Docker sandbox reproducibility. Wrap real data in interactive environments featuring sandboxed application state, MCP servers, and browser layers for buyers to train and evaluate agents. Partner with technical stakeholders at AI labs and RL-environment providers to shape derivative products that maximize asset value. Prototype quickly, then harden successful ideas into scalable, repeatable pipelines while maintaining strict security, privacy, and licensing standards for sensitive proprietary materials.
Required Qualifications
- Candidates MUST be located in the New York City Metro area
- RL-environments / AI-training background (critical): you've built RL environments and/or products used to train or evaluate models — environments, agentic task suites, evals, benchmarks, or verifiers
- Experience: 4–8 years of engineering experience, with meaningful time in the RL-environments, AI-training-data, or model-evaluation ecosystem (at a lab, an RLE/eval company, or a team that shipped training environments or products)
- Core engineering: strong Python, containers (Docker), and CI/test infrastructure; comfort building reproducible sandboxes from messy real-world code and data
- Evals & verification: familiarity with LLM evaluation and agent harnesses (SWE-bench-style setups, Verifiers, HUD, or similar) and with verifier/reward design, including resistance to reward hacking
- Education: Bachelor's or Master's in Computer Science, Machine Learning, or a related field — or equivalent practical experience
Desired Qualifications
- Nice to have: contributions to public benchmarks or eval frameworks; experience with post-training / fine-tuning data; simulation or frontend skills (MCP, Playwright) for world-building
- Team Management: experience building and managing a team of engineers, a plus
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.