Machine Learning Engineer

Locus Robotics is a global leader in warehouse automation, delivering unmatched flexibility and unlimited throughput, and actionable intelligence to optimize operations. Powered by LocusONE, an AI-driven platform, our advanced autonomous mobile robots seamlessly integrate into existing warehouse environments to enhance efficiency, reduce costs, and scale operations with ease.

Trusted by over 150 industry leading retail, healthcare, 3PL, and industrial brands in over 350 sites worldwide, Locus enables warehouse operators to achieve rapid ROI, minimize labor costs, and continuously improve productivity. Our industry-first Robots-as-a-Service (RaaS) model ensures ongoing innovation, scalability, and cost-effectiveness without the burden of significant capital investments. With proven capabilities in diverse workflows—from picking and replenishment to sorting and pack-out—Locus Robotics empowers businesses to meet peak demands and adapt to ever-changing operational needs.

Are you a Machine Learning Engineer with a passion for reinforcement learning, multi-agent systems, and simulation at scale? We want to hear from you!

At Locus Robotics, we’re developing advanced simulation tools and ML systems to optimize the behavior of large autonomous fleets in dynamic environments. In this role, you will work on cutting-edge reinforcement learning (RL) models, multi-agent systems, and faster-than-real-time simulations to drive innovation in logistics, robotics, and beyond. You’ll collaborate with a highly skilled team of engineers and data scientists to develop scalable ML models and deploy them into production environments using modern MLOps practices.

If you're excited about solving real-world optimization problems, building high-performance ML infrastructure, and working with autonomous agent simulations, this is your opportunity to make a significant impact.

This is a remote position based in England, Scotland, Portugal, Poland, or Spain. Candidates must be authorized to work in one of these countries without the need for work sponsorship.

Responsibilities: 

• Utilize, develop, and enhance simulation tooling and infrastructure to enable faster-than-real-time modelling of 1,000+ autonomous agents for various use cases such as fleet optimization, logistics, or robotics.
• Develop, deploy, and maintain machine learning models, with a strong focus on reinforcement learning (RL) and multi-agent systems to optimize fleet behavior in dynamic environments.
• Implement and improve MLOps pipelines to support continuous training, deployment, monitoring, and scaling of machine learning models in production.
• Collaborate with data engineers and software developers to ensure seamless integration of machine learning models with existing infrastructure and data pipelines.
• Stay up to date with advancements in reinforcement learning, distributed computing, and ML frameworks to drive innovation in the organization.
• Work with cloud-based solutions (AWS, GCP, or Azure) to deploy and manage machine learning workloads in a scalable manner.

• Master’s degree or Ph.D. in Data Science, Computer Science, Mathematics, or a related field.
• 4+ years of hands-on experience designing and deploying machine learning models in production, with a focus on reinforcement learning (RL) and multi-agent systems (MAS).
• Advanced Python programming skills, with a strong emphasis on writing efficient, scalable, and maintainable code.
  
• Proven experience with TensorFlow/PyTorch/Jax, Scikit-learn, and MLOps workflows for training, deployment, and monitoring of ML models.
• Experience working with Polars and/or Pandas for high-performance data processing.
  
• Proficiency with cloud platforms (AWS, GCP, or Azure), including containerization and orchestration using Docker and Kubernetes.
  
• Hands-on experience with reinforcement learning frameworks such as OpenAI Gym or Stable-Baselines3.
  
• Practical knowledge of optimization algorithms and probabilistic modeling techniques (e.g., Bayesian methods, Gaussian Belief Propagation).
  
• Experience integrating models into real-time decision-making systems or multi-agent RL environments (MARL).
  
• Exposure to spatiotemporal data analysis, including time-series anomaly detection and forecasting.
  
• Familiarity with ROS (Robot Operating System) for robotics or simulation integration.
  
• Publications in top-tier conferences/journals (e.g., NeurIPS, ICML, ICRA, CVPR, ECCV, ICCV) are a plus.
  
• Proficient English written and verbal communication skills required to collaborate effectively with internal and external teams.
  
• Excellent analytical and problem-solving skills, with the ability to contribute effectively in a collaborative team environment.