Reinforcement Learning Research Engineer – Exploration & Decision Intelligence (m/w/d)

{
  "content_hash": "a5cc94af1ce7db23b1c96e46029a7053c76fa8fb0187956496deb9233fa531f2",
  "source_hash": "a974178670d19c2e268ff30972f4665f1345885107f21fabd2c58ac35694cc9d",
  "last_changed_at": "2026-05-30T05:52:53.220Z",
  "active_status": "active"
}

{
  "language": "en",
  "location": {
    "raw": "Munich (DEU)",
    "city": null,
    "region": null,
    "country": "Munich (DEU)",
    "is_remote": false,
    "confidence": 0.8
  },
  "salary_max": null,
  "salary_min": null,
  "inferred_at": "2026-06-06T07:53:15.906Z",
  "launch_scope": {
    "reason": "personio_production_catalog",
    "included": true,
    "location": {
      "raw": "Munich (DEU)",
      "city": null,
      "region": null,
      "country": "Munich (DEU)",
      "is_remote": false,
      "confidence": 0.8
    },
    "countries": [
      "Munich (DEU)"
    ]
  },
  "remote_policy": null,
  "salary_period": null,
  "workplace_type": null,
  "salary_currency": null
}

{}

{
  "id": "2594292",
  "name": "Reinforcement Learning Research Engineer – Exploration & Decision Intelligence (m/w/d)",
  "office": "Munich (DEU)",
  "keywords": [],
  "schedule": "full-time",
  "createdAt": "2026-04-08T09:50:43+00:00",
  "seniority": "experienced",
  "department": "Engineering & Tech",
  "occupation": "software_and_system_architecture",
  "subcompany": "Autonomous Teaming Solutions ATS GmbH",
  "employmentType": "permanent",
  "jobDescriptions": [
    {
      "name": "What we offer",
      "value": "<ul style=\"border:0px solid;color:rgb(32,32,32);font-family:Inter, '-apple-system', BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Open Sans', 'system-ui', '-apple-system', 'Segoe UI', Roboto, Ubuntu, Cantarell, 'Noto Sans', sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji';font-size:14px;font-style:normal;font-weight:400;text-transform:none;background-color:rgb(255,255,255);\"><li style=\"border:0px solid;margin:0px;\">Opportunity to work on a new solution from scratch in a technical complex environment</li><li style=\"border:0px solid;margin:0px;\">Work in an international, agile, cross-functional team creating the future of autonomous systems</li><li style=\"border:0px solid;margin:0px;\">Grow your career in a expanding and ambitious engineering team</li><li style=\"border:0px solid;margin:0px;\">Build innovative products using state-of-the-art technologies in AI, robotics, and autonomy </li><li style=\"border:0px solid;margin:0px;\">Benefit from a steep learning curve and continuous development</li><li style=\"border:0px solid;margin:0px;\">Enjoy team events and a strong, collaborative culture</li></ul>"
    },
    {
      "name": "Your mission",
      "value": "<div style=\"border:0px solid;margin:0px;color:rgb(32,32,32);font-family:Inter, '-apple-system', BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Open Sans', 'system-ui', '-apple-system', 'Segoe UI', Roboto, Ubuntu, Cantarell, 'Noto Sans', sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji';font-size:14px;font-style:normal;font-weight:400;text-transform:none;background-color:rgb(255,255,255);\">Build real autonomous systems that operate in the real world, not in the lab. </div><br><div style=\"border:0px solid;margin:0px;color:rgb(32,32,32);font-family:Inter, '-apple-system', BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Open Sans', 'system-ui', '-apple-system', 'Segoe UI', Roboto, Ubuntu, Cantarell, 'Noto Sans', sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji';font-size:14px;font-style:normal;font-weight:400;text-transform:none;background-color:rgb(255,255,255);\">Join our engineering team of a new product and help build the core autonomy that powers our next generation robotic systems used for defense and mission-critical operations. You will design, implement, and harden robotic software that must perform under real operational conditions - outdoors, under uncertainty, with real consequences. Your work will directly shape the reliability, safety, and tactical capability of the systems we deliver. </div><div style=\"border:0px solid;margin:0px;color:rgb(32,32,32);font-family:Inter, '-apple-system', BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Open Sans', 'system-ui', '-apple-system', 'Segoe UI', Roboto, Ubuntu, Cantarell, 'Noto Sans', sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji';font-size:14px;font-style:normal;font-weight:400;text-transform:none;background-color:rgb(255,255,255);\"> </div><ul><li><span style=\"font-size:inherit;\">Research and prototype novel RL algorithms (e.g. exploration, POMDPs, multi-agent systems) </span></li><li><span style=\"font-size:inherit;\">Define, design and implement use-cases for DRL on edge devices </span></li><li><span style=\"font-size:inherit;\">Translate theory into scalable systems with support from our engineering teams </span></li><li><span style=\"font-size:inherit;\">Collaborate with simulation, autonomy and AI infrastructure teams </span></li><li><span style=\"font-size:inherit;\">Develop decision-making for intelligent behavior and architectures </span></li></ul>"
    },
    {
      "name": "Your profile",
      "value": "<ul><li><span style=\"font-size:inherit;\">Deep knowledge of RL theory and practice: policy gradients, value iteration, Q-learning, etc. </span></li><li><span style=\"font-size:inherit;\">Experience with ML training in physics based simulation (Gazebo, IsaacSim, Mujoco, Carla, etc.).</span></li><li><span style=\"font-size:inherit;\">Strong Programming proficiency (Python, C/C++).</span></li><li><span style=\"font-size:inherit;\">Comfortable with ML tooling and maintaining ML pipelines (Pytorch Lightning, MlFlow, etc.).</span></li><li><span style=\"font-size:inherit;\">Have experience with deploying ML methods to physical devices.</span></li><li><span style=\"font-size:inherit;\">Experience with version control (git).</span></li><li><span style=\"font-size:inherit;\">Familiarity with statistics, evaluation methods and experiment design.</span></li><li><span style=\"font-size:inherit;\">You think rigorously and build practically.</span></li></ul>"
    },
    {
      "name": "Nice to have",
      "value": "<ul><li><span style=\"font-size:inherit;\">PhD in Reinforcement Learning, Robot Engineering or equivalent with experience in deploying developed methods to real robots.</span></li><li><span style=\"font-size:inherit;\">OR masters degree in relevant field with extensive experience in RL.</span></li><li><span style=\"font-size:inherit;\">Experience with sensor based end-to-end ML architectures.</span></li><li><span style=\"font-size:inherit;\">Familiar with Transformers, Attention, Graphs, VLAs and other modern day ML building blocks.</span></li><li><span style=\"font-size:inherit;\">Publications at NeurIPS, ICLR, ICML, ICRA, IROS, etc. are a plus </span></li><li><span style=\"font-size:inherit;\"><span>Experience with robotics middleware (ISAAC, ROS/ROS2, etc.)</span></span></li></ul>"
    },
    {
      "name": "Why us?",
      "value": "<ul style=\"border:0px solid;color:rgb(32,32,32);font-family:Inter, '-apple-system', BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', 'Open Sans', 'system-ui', '-apple-system', 'Segoe UI', Roboto, Ubuntu, Cantarell, 'Noto Sans', sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji';font-size:14px;font-style:normal;font-weight:400;text-transform:none;background-color:rgb(255,255,255);\"><li style=\"border:0px solid;margin:0px;\">Willingness to travel</li><li style=\"border:0px solid;margin:0px;\">Citizenship of NATO member country or closed allied are mandatory</li></ul>"
    }
  ],
  "occupationCategory": "it_software",
  "recruitingCategory": "Recruitingprozess ATS - Tech"
}