Multi-Agent Reinforcement Learning Intern

Laelaps AI
Laelaps AI

Posted on Sep 19, 2026
Apply now

Our Mission

At Laelaps AI, we believe robotics is entering a transformative decade, much like the arrival of the internet. Advances in AI, cloud computing, and hardware are reshaping what autonomous systems can do. Our mission is to build the intelligent software that powers physical security in the real world - enabling robots and sensors to handle dangerous and critical tasks that humans shouldn't have to. By engineering the orchestration layer for intelligent security, we aim to create a world that is safer, more secure, and more resilient.

We're a strong founding team based in Zurich, backed by visionary investors and advisors. We are engineering the future of security today!

The Role

As a Multi-Agent Reinforcement Learning Intern, you'll develop learning-based coordination strategies for fleets of robots that share tasks, optimize throughput, and remain safe under uncertainty. You'll work at the intersection of RL research and real-world robotics, taking ideas from papers and pushing them toward deployment on multi-robot systems.

This role is highly practical: you'll design environments, train policies, evaluate against safety and throughput metrics, and contribute to the simulation infrastructure that makes serious RL work possible. You'll learn how to take MARL ideas from sim to systems that operate reliably under real constraints.

What You'll Work On

  • Design simulation environments for multi-robot coordination tasks.
  • Train and evaluate MARL policies for task allocation, coordination, and safety.
  • Run experiments on coordination tradeoffs: throughput, robustness, safety under failure.
  • Contribute to sim-to-real transfer pipelines.
  • Integrate learned coordination policies with the broader autonomy stack.
  • Apply solid engineering practices: experiment tracking, reproducibility, evaluation discipline.

    • Who We're Looking For

    We're looking for a motivated student excited to apply academic training in a fast-moving startup. You'll be surrounded by a team that values learning, experimentation, and building things that actually work in the real world.

    Your Background:

  • Currently pursuing PhD or recently completed a Master's degree in Machine Learning, Robotics, or a closely related field.
  • Strong understanding of reinforcement learning fundamentals.
  • Familiarity with multi-agent RL methods.
  • Strong PyTorch (or JAX) skills.
  • Good coding skills in Python.
  • Comfortable using Docker and Git in your workflows.

    • Nice to Have:

  • Publications at top ML or robotics venues (NeurIPS, ICML, CoRL, RSS, ICRA).
  • Experience with robotics simulators (IsaacSim, MuJoCo, Gazebo).
  • Background in sim-to-real transfer or domain randomization.
  • Exposure to real-robot deployment.

    • What We Offer

  • Mission: Build the foundation models that decide how robots see, reason, and act in the real world. Research with deployment, not papers without impact.
  • Autonomy: Real independence on what to train, how to evaluate, and how to ship.
  • Compute: Access to the compute and field data you need to do serious work.
  • Team: Work alongside PhD-level co-founders in AI, Robotics, and Physics, plus a strong founding engineering team.
  • Location: In-person in Zürich, Switzerland.
  • Culture: Small, international founding team that's serious about building, but doesn't take itself too seriously. Curiosity and quirks welcome.
    • Apply now
    See more open positions at Laelaps AI