AI Engineer - Task Planning and Orchestration, Embodied Agents (human)

Atlas Metrics; Riederich; Vor Ort; EUR 70.000 - 110.000; Vollzeit

Benefits dieser Stelle

30 vacation days

Exclusive employee discounts

Competitive salary package

Zusammenfassung

Neura Robotics in Riederich seeks an AI Engineer to advance cognitive capabilities of humanoid robots, focusing on embodied agents, long-horizon planning, and robust perception.

You will design the agent loop from sensor input to reasoning to action, ground language with vision using VLMs, and collaborate with software, hardware and product teams to deploy reliable behavior on real robots and in simulation.

Qualifikationen

• Master's or PhD in Computer Science, Robotics, or related field.
• Demonstrated experience building agent systems on top of LLMs and VLMs.
• Hands-on work with physical robots (not only simulation).
• Experience grounding language with vision and maintaining state over long horizons.
• Familiarity with hierarchical autonomy and subgoal interfaces.
• Experience with robotics middleware and onboard deployment; ROS 2.
• Excellent English; German a plus.

Aufgaben

• Embodied agent harness: design loop from sensor input to reasoning to action, its interfaces to the robot's cameras, depth, and proprioception, and the state management that keeps a task coherent over minutes rather than seconds.
• Task decomposition & long-horizon planning: Turn high-level human intent into ordered, executable steps with preconditions and success criteria.
• Visual reasoning & world state: Use VLMs to interpret the scene, ground language, and maintain objects, affordances, and task history for the planner.
• Closed-loop execution & recovery: Verify each step against observation, detect divergence, and replan or escalate when needed.
• Evaluation on the robot: Measure task success in simulation and on real hardware, build failure taxonomies to guide fixes.
• Cross-functional collaboration: Work with foundation model, perception, manipulation, and hardware teams.

Kenntnisse

Embodied agent systems

LLM/VLM integration

Robot cognition

ROS 2

English language proficiency

German language (nice to have)

Ausbildung

Master's or PhD in Computer Science, Robotics, or related field

Tools

ROS 2

Jobbeschreibung

AI Engineer - Task Planning and Orchestration, Embodied Agents (human)

Neura Robotics • Riederich

Give Our Robots Consciousness

In the AI Department, you'll develop the cognitive abilities of our robots, enabling them to understand and interact with their surroundings. You'll work on algorithms that make machines intelligent and adaptive—ranging from object recognition and language processing to decision-making in complex environments. You'll be part of a team that pushes technological boundaries and collaborates closely with software, hardware, and product management teams. Using cutting‑edge tools and methods from machine learning and AI, you'll work on projects that have a direct impact on our products. If you're excited about making machines smarter and shaping the future of human‑machine interaction, the AI Department is the perfect place for you.

Full-time

Riederich

from today

At NEURA Robotics, cognitive robots don't just execute commands. They perceive, reason, plan over long horizons, and act autonomously in the physical world. Our robotic foundation models handle the physical execution. What sits above them is the agent: the part that works out what a task actually requires, breaks it into steps the robot can carry out, and notices when reality has stopped matching the plan. We're looking for an engineer to help build those agents for our humanoid platform.

Your Mission & Challenges

• Embodied agent harness: Design and build the agent that runs on our humanoid platform — the loop from sensor input to reasoning to action, its interfaces to the robot's cameras, depth, and proprioception, and the state management that keeps a task coherent over minutes rather than seconds.

• Task decomposition & long-horizon planning: Turn high-level human intent into ordered, executable steps, each with the preconditions, spatial references, and success criteria it needs, and sequence them so the robot can work through a task it has never seen in that exact form before.

• Visual reasoning & world state: Use VLMs to interpret what the robot is looking at, ground language in the scene, and maintain a working representation of objects, affordances, and task history for the planner to reason over.

• Closed-loop execution & recovery: Verify each step against observation instead of assuming success, detect divergence from the plan, and replan, retry, or escalat to a human when the risk is too high.

• Evaluation on the robot: Measure task success in simulation and on real hardware, build failure taxonomies from real runs, and use them to decide whether a fix belongs in the planner, the interface, or the step being issued.

• Cross-functional collaboration: Work closely with our foundation model, perception, manipulation, and hardware teams to take the reasoning layer above the models from concept to reliable behavior on a deployed robot.

What We Can Look Forward To

• A strong Master's or PhD in Computer Science, Robotics, or a related field — or equivalent depth shown through shipped work.

• Demonstrated experience building agent systems on top of LLMs and VLMs that decompose tasks, plan, use tools, and maintain state over long horizons, rather than single-turn prompt work.

• Several years of hands‑on work on physical robots, not only in simulation: bringing your own code onto a real platform, running it there, and debugging a system that behaved differently once it had a body.

• Hands‑on experience with VLMs as a working tool: grounding language in images, spatial and physical reasoning, structured output you can act on, and a realistic sense of where they fail.

• Familiarity with hierarchical autonomy, where a reasoning model plans and learned or classical policies execute: subgoal interfaces, progress verification, replanning.

• Experience with robotics middleware and onboard deployment: ROS 2, inference on embedded GPUs, and working inside a real latency budget.

• Solid software engineering: clean code, testing, and services other teams can build against. Cloud, containerization, and CI/CD experience is a plus.

• Excellent English. German is a plus.

Creative Freedom and Agility

Enjoy a dynamic, self‑reliant work culture with flat hierarchies, flexible hours, and 30 vacation days. Ideal for those seeking an inspiring professional setting, whether you're starting out or an experienced exec.

Passion for Winning

A passionate and highly skilled team of international experts aiming to redefine robot assistants.

Attractive Compensation

Enjoy a competitive salary package along with exclusive employee discounts.

One Team

Whether it's a summer party or company town hall meetings, we celebrate our successes together.

Professional Growth

Support for your personal and professional development.

Our values. The cornerstones of our success.

STRONGER TOGETHER

We are a team. We strive to achieve great things by promoting the success of our colleagues and partners.

PASSION DRIVES US

We strive for technological progress in order to give people back their valuable time for enjoyable activities.

MAKING A CHANGE

We strive to revolutionize the world of robotics by pushing the boundaries of technology every day.

TRUST AND HONESTY

We live a high level of appreciation through open communication and transparency.

WE SPEED THINGS UP

We do our best to always be two steps ahead. We achieve this through empowerment, freedom of action and personal responsibility.

WE ARE HUMAN

People are at the center of everything we do.

Our Location

Headquarters: Innovate in Riederich, Live in Metzingen and Stuttgart

Our headquarters in Metzingen and Riederich are the heart of our company. It's not just home to our offices, but also our production facilities, Academy, logistics, and Tech Labs—all working together to turn ideas into reality. Riederich itself is a small, peaceful town, just a kilometer away from Metzingen, a city with its own unique character. Metzingen is globally renowned as Outlet City, attracting visitors from all over the world. Here, you can enjoy exclusive designer stores in a relaxed and charming setting. The city also offers a variety of restaurants, cafés, and a down-to-earth Swabian coziness—perfect for unwinding after work.

Unsere Mission

David Reger, Gründer und CEO

"Our goal was to develop the world's first cognitive robot that can work with people, learn from them and provide them with targeted support. And that is exactly what we have achieved. But there is much more to come!"

Sounds interesting?