Senior Reinforcement Learning Engineer - Remote

United States Digital Space LLC; United States; Remote; USD 100,000 - 150,000; Full time

Job summary

Bright Vision Technologies is seeking a Machine Learning Engineer - RL to design, train, and deploy reinforcement learning based systems for high‑impact decision making where supervised learning falls short. The role demands deep RL knowledge, simulation environments, reward modeling, and production‑grade deployment.

This is a 100% remote, full‑time position in the United States with sponsorship constraints; you will collaborate with researchers and engineers to ship robust RL solutions at scale

Qualifications

• Six or more years of combined RL research and engineering experience.
• Strong proficiency in Python and modern deep learning frameworks.
• Hands-on experience with at least one major RL library or in-house RL stack.
• Experience designing reward functions and working with simulation environments.
• Experience training neural networks on GPU clusters.

Responsibilities

• Design and implement RL solutions for sequential decision making in real and simulated environments.
• Develop simulation environments for large-scale agent training.
• Implement and evaluate RL algorithms including policy gradient and offline RL methods.
• Engineer reward functions and alignment with safety constraints.
• Build scalable RL training infrastructure and data pipelines.
• Monitor deployed policies for drift and safety and document results.

Skills

Python

Deep learning frameworks

Reinforcement Learning

GPU clusters

Experimentation and debugging

Education

Master’s or PhD in Computer Science, Machine Learning, or related field

Tools

RL libraries

in-house RL stack

Job description

Bright Vision Technologies is seeking a Machine Learning Engineer - RL to design, train, and deploy reinforcement learning based systems for high‑impact decision making where supervised learning falls short. The role demands deep RL knowledge, simulation environments, reward modeling, and production‑grade deployment.

This is a 100% remote, full‑time position in the United States with sponsorship constraints; you will collaborate with researchers and engineers to ship robust RL solutions at scale