Reinforcement Learning Engineer

5 hours, 50 minutes ago
Full-time
Junior
Data Science and Analytics

Code Metal

Code Metal builds verifiable code translation software for mission-critical industries. Its platform translates code across languages and hardware architectures, then verifies correctness, compliance, and performance for use cases like edge development, code portability, and code modernization.

Software Development
51-200
Founded 2023
$178M raised

Description

  • Build and maintain robust distributed training systems using PyTorch.
  • Design and implement scalable data curation and quality assurance pipelines for training datasets.
  • Develop orchestration tools to manage complex workflows across large-scale model training and evaluation.
  • Research and develop evaluation frameworks for AI model performance.
  • Build reinforcement learning solutions, including approaches using Reinforcement Learning with Human Feedback (RLHF).
  • Apply RLHF to large language models, with an emphasis on code generation tasks.
  • Engage with frontier research through open-source work and potential publications.
  • Support practical AI projects that address real-world challenges for leading chip manufacturers.

Requirements

  • 2+ years of experience in distributed training, preferably with PyTorch.
  • Strong background in reinforcement learning.
  • Recent experience with RLHF is highly preferred.
  • Proven ability to build data curation and quality assurance pipelines.
  • Experience developing evaluation frameworks.
  • Experience across both data pipeline and orchestration work is ideal.
  • Eligibility for TS/SCI clearance.
  • Contributions to open-source AI or ML projects are nice to have.
  • Published work or demonstrable research experience in related fields is nice to have.
  • Hands-on experience applying RLHF to LLMs, especially for code generation, is nice to have.
  • Experience with large-scale synthetic data generation is nice to have.

Benefits

  • 100% employer-paid health care coverage, including medical, dental, and vision.
  • 401(k) with 5% matching.
  • Uncapped vacation plus sick leave and public holidays.
  • Flexible hybrid work arrangement.
  • Relocation assistance for qualifying employees.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Research Engineer - Geometry Processing

Foundation EGI 11-50 Technology, Information and Internet

Research Engineer - Geometry Processing at an MIT-born, venture-backed startup building an AI copilot for design and manufacturing, focused on applying AI, physics simulation, and computer graphics to improve engineering productivity across the product development workflow.

LLM Machine Learning Python Reinforcement Learning
5 hours, 35 minutes ago

Research Engineer - Computational Design

Foundation EGI 11-50 Technology, Information and Internet

Research Engineer - Computational Design at an MIT-born, venture-backed startup building an AI copilot for design and manufacturing, focused on reducing engineering costs and improving productivity across the design and manufacturing process.

LLM Machine Learning Python Reinforcement Learning
5 hours, 35 minutes ago

Binance Accelerator Program - Data Scientist (LLM & Trading)

Binance 5K-10K Capital Markets

Binance is hiring a Binance Accelerator Program Data Scientist in Hong Kong/Taipei to help develop and deploy AI-powered financial trading systems built on Web3 data and large language models.

Blockchain LLM PyTorch Reinforcement Learning TensorFlow
1 day, 11 hours ago

Forward Deployed Senior Data Scientist

Govini 51-250 Professional Services

Govini is seeking a Data Scientist to develop and deploy AI-driven solutions for defense acquisition and national security decisions using proprietary and commercial data.

AWS Azure GCP LLM Machine Learning MLOps Prototyping
2 days, 3 hours ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers