Description :

We are hiring RL Environments Engineers to design and build machine learning engineering (MLE) environments focused on teaching large language models (LLMs) advanced concepts from modern AI and machine learning.

This is a remote contract role requiring at least 4 hours of overlap with PST and strong written & spoken English skills.

Key Responsibilities :

- Design and implement interactive RL environments for training and evaluating LLMs

- Translate complex research ideas into practical RL / RLVR tasks

- Build production-quality Python systems with a focus on reliability and speed

- Iterate quickly based on feedback and throughput expectations

- Collaborate with research and engineering teams on advanced AI problems

Minimum Qualifications :

- Strong Python engineering skills (production-quality code, not notebook-only)

- Clear understanding of LLMs and their current limitations

- Strong debugging mindset with a focus on reliability and iteration speed

- Ability to respond quickly to feedback and meet throughput expectations

You may be a great fit if you have experience in one or more of the following :

1. Deep understanding of Transformer internals and modern LLM training or inference

2. Hands-on experience with inference libraries such as vLLM, SGLang, etc.

3. Strong expertise in CUDA or Pallas kernel development

4. Active ML / DL researcher with publications or open-source contributions

5. Experience building complex RL environments or open-ended RL-based learning systems

Additional Details :

Work Mode : Remote (Contract)

Time Overlap : Minimum 4 hours with PST

Experience : 1 - 2 years