Verita AI

Verita AI is at the forefront of next-generation artificial intelligence, emphasizing nuance, multimodal reasoning, and human judgment. We are dedicated to building high-trust data pipelines for training and evaluating models.

Our founding team comes from Mercor, Stanford, HRT, Citadel, Stripe and Yale. We partner with world-class researchers and engineers to advance experimentation, rigor, and reliability in the field of AI.

https://www.verita-ai.com/

Brief Description:

We’re hiring RL Environments Engineers to design and build MLE environments. The goal is to teach LLMs advanced concepts from modern AI/ML.

Compensation:

• $50–$150 USD per hour(dependent on the expertise level and quality of take-home assignment).
• $500 bonus for the take-home assignment if offered a job.

Technical Evaluation:

If you are interested in exploring this role, please complete:

Verita AI | RL Environment Engineer Technical Screening

https://form.typeform.com/to/OFHwbf2E

Requirements:

• Master’s degree in Computer Science, Artificial Intelligence, Machine Learning, or a related technical field.
• Strong Python skills (engineering-quality, not notebook-only).
• Production mindset including debugging, reliability, and iteration speed.
• Clear understanding of LLMs and their current limitations.
• Advanced English proficiency (C1/C2).
• Ability to meet throughput expectations and respond quickly to feedback.
• Complete an average of two tasks each week.
• Turn the take-home assignment into a complete task using company tools and guidelines upon onboarding.

You may be a good fit if:

• You have a deep understanding of transformer internals, training/inference of modern LLMs, or experience with inference libraries (vLLM, SGLang, etc).
• Expertise in CUDA or Pallas kernel development optimizing non-trivial neural modules to specific hardware
• Expert knowledge in an active DL/ML research area, with publications or public code to show for it.
• You have strong fundamentals and broad research interests, you read many papers, understand them deeply and have creativity to translate them into RLVR problems
• You have built complex interactive RL environments and have strong insights into open-ended RL-based learning systems

Additional Details

• Time Commitment: At least 4 hours overlap to UTC-8 (PST 9am–5pm).
• Process: Includes a HackerRank take-home assignment (2–5 hours average) with a one-week turnaround.
• Any questions, reach out to [email protected] or [email protected]

Job Type: Contract

Pay: $50.00 - $150.00 per hour

Expected hours: No less than 20 per week

Work Location: Remote