Remote Reinforcement Learning Engineer – Autonomy

BairesDev; Colombia; Presencial; COP 376.400.000 - 564.600.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Remote work from anywhere

Competitive USD compensation

Home equipment provided

Flexible hours

Parental leave and holidays

Global, multicultural team

Mentorship and career growth

Descripción de la vacante

BairesDev is seeking a Reinforcement Learning Engineer to develop autonomous decision-making systems and optimize RL policies. You will design reward structures, build simulations with OpenAI Gym, and collaborate with data and research teams to deploy robust AI solutions.

Join a 100% remote team with global impact, competitive USD compensation, and flexible scheduling while working with top 1% talent across the world.

Formación

• 4+ years of experience in AI/ML, robotics, or data science.
• Proven expertise in developing and optimizing reinforcement learning systems.
• Proficiency in using OpenAI Gym and environment simulation tools.
• Strong background in policy optimization and reward design.

Responsabilidades

• Design and implement reinforcement learning algorithms for autonomous decision-making.
• Develop and manage environment simulations for training and testing agents using OpenAI Gym.
• Define and refine reward functions to align agent behavior with desired performance outcomes.
• Optimize RL policies through advanced experimentation and algorithm tuning.
• Collaborate with data and research teams to integrate RL models into broader AI systems.
• Monitor and evaluate the performance of RL systems in simulated and production environments.

Conocimientos

Reinforcement Learning

AI/ML

Autonomous systems

Policy optimization

Experimentation

English communication

Herramientas

Python

OpenAI Gym

PyTorch

Descripción del empleo

BairesDev is seeking a Reinforcement Learning Engineer to develop autonomous decision-making systems and optimize RL policies. You will design reward structures, build simulations with OpenAI Gym, and collaborate with data and research teams to deploy robust AI solutions.

Join a 100% remote team with global impact, competitive USD compensation, and flexible scheduling while working with top 1% talent across the world.