Remote RL Engineer - Scale & Deploy RL Policies

Bright Vision Technologies; San Diego, 4S Ranch (CA, CA); Remote; USD 80,000 - 100,000; Full time

Job summary

Bright Vision Technologies is seeking a RL Engineer for a 100% remote role in the United States. You will design, train, and deploy RL-based systems for high-impact decision-making, with focus on scalable training, evaluation, and production deployment.

The ideal candidate has a strong research background plus engineering pragmatism, with 6+ years of RL experience and expertise in Python, DL frameworks, and RL libraries. Collaboration across teams and effective communication are essential.

Qualifications

• Master's or PhD in Computer Science, ML, or related field, or equivalent experience.
• Six+ years of RL research and engineering experience.
• Strong Python and modern DL frameworks.
• Hands-on experience with major RL libraries and reward design.
• Familiar with simulation environments and large-scale data collection.
• Experience training neural policies on GPU clusters.
• Strong communication skills and a track record of impactful RL work.

Responsibilities

• Design, train, and deploy RL-based systems for high-impact decisions.
• Scale training and evaluate policies across large environments.
• Bridge RL research and production, ensuring stability and safety.

Skills

Python

Deep learning

RL libraries

Reward modeling

Simulation environments

GPU training

Communication

Production deployment

Education

Master's or PhD in CS/ML

Tools

OpenAI Gym

PyTorch

TensorFlow

Ray RLlib

Job description

Bright Vision Technologies is seeking a RL Engineer for a 100% remote role in the United States. You will design, train, and deploy RL-based systems for high-impact decision-making, with focus on scalable training, evaluation, and production deployment.

The ideal candidate has a strong research background plus engineering pragmatism, with 6+ years of RL experience and expertise in Python, DL frameworks, and RL libraries. Collaboration across teams and effective communication are essential.