Research Engineer – Reinforcement Learning

🔥 12 hours ago

🇺🇸 United States – Remote

💵 $230k - $450k / year

⏰ Full Time

🟡 Mid-level

🟠 Senior

📚 Research Engineer

🦅 H1B Visa Sponsor

This company has sponsored H1B visas in the past.

👻 Ghost score 21%

What it means: the chance that no one is really hiring for this job.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Harvey

WebsiteLinkedInAll Job Openings

11 - 50 employees

🤖 Artificial Intelligence

⚖️ Legal

🏢 Enterprise

💰 $80.6G Series B on 2023-12

Artificial Intelligence • Legal • Enterprise

Harvey is a professional class AI solution tailored specifically for law firms, professional service providers, and Fortune 500 companies. It offers a suite of domain-specific tools that enable users to delegate complex tasks in natural language to a customized personal assistant. Harvey's platform facilitates rapid research with grounded results across legal, regulatory, and tax domains, while also providing secure project workspaces for document analysis through generative AI. With a focus on enterprise-grade security and industry-leading AI models, Harvey aims to streamline workflows and free professionals, such as lawyers, from mundane tasks, enabling them to concentrate on strategic and advisory roles.

📋 Description

• Own and pursue a research agenda to improve model capability on long-horizon legal reasoning and agentic workflows • Design and run post-training experiments across SFT and RL using leading open-weight models • Develop reward functions and verifiers for semi-verifiable tasks, including rubrics, learned preference models, and expert preference data • Study where reward functions and verifiers break • Run and debug training at scale, addressing divergence, reward hacking, and instability • Build and use rigorous evaluations to track improvements and decide what ships • Design, implement, test, and debug code across the research stack • Carry research ideas from experiments through training runs to models used by customers • Own post-training recipes across supervised fine-tuning and reinforcement learning

🎯 Requirements

• Hands-on experience post-training LLMs with SFT and RL, including preference optimization • Direct ownership of training runs and results • Deep ML fundamentals • Experience getting distributed training runs working reliably • Strong engineering skills in Python • Production-quality code and end-to-end system ownership • Research experience in RL for language models or reward modeling • Ability to move quickly from experiments to shipped improvements • Publications welcome, not required • Must be legally authorized to work in the United States • Must be able to work in the United States or obtain employment visa sponsorship as applicable

🏖️ Benefits

• Equity plan • Comprehensive health coverage • Dental coverage • Vision coverage • Retirement benefits with 401(k) match up to 4% • Flexible PTO • Equal opportunity employer • Reasonable accommodations for applicants with disabilities

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume