--- title: 'Senior Reinforcement Learning Engineer at Gravis Robotics' canonical: 'https://feeny.ai/job/senior-reinforcement-learning-engineer-gravis-robotics-zurich-dg38zww2vz24' type: 'job' last_seen: '2026-09-07' --- # Senior Reinforcement Learning Engineer at Gravis Robotics - **Company:** Gravis Robotics - **Location:** Zurich, Switzerland - **Employment:** full-time - **Work type:** hybrid - **Posted:** 2026-06-24 - **Last confirmed live:** 2026-09-07 - **Apply:** https://jobs.lever.co/gravisrobotics/fe9d2c3e-84d6-4b0f-ad31-70176d175c5c ## Job description Gravis Robotics is a high-growth Series A start-up backed by SoftBank, bringing Physical AI to the construction industry, turning heavy construction machines into autonomous robots. Gravis began as an ETH Zurich spin-out, and our unique combination of learning-based automation and augmented remote control lets one operator safely conduct a fleet of earthmoving machines in a gamified environment. Backed by deep robotics research and now deployed across multiple countries with leading construction and equipment partners, our team is rapidly growing to bring this technology to a trillion-dollar industry. ## About the Job The autonomy team at Gravis builds autonomous systems for excavators operating in real construction environments. You will build control modules that run on many different machines, across many sites, with different soil conditions. We’re looking for a roboticist with data driven planning and/or control background, deep python expertise and good level of C++ proficiency. To be successful in this role you should have experience working with real robots, tackling the challenges of sim2real transfer, and deploying robotic systems in a production environment. The autonomy team at Gravis builds autonomous systems for excavators operating in real construction environments. In this role, you will develop control modules designed to run across diverse machines, sites, and soil conditions. We are looking for a roboticist with a background in data-driven planning and/or control, strong Python skills, and a solid working knowledge of C++. To thrive in this role, you should have experience working with physical robots, navigating the challenges of sim-to-real (sim2real) transfer, and deploying robotic systems into production environments. ## What you will do Learning-Based Planning and Control for Real Systems - Develop data driven planning and control systems for autonomous excavation that generalize across machine models and soil conditions - Contribute to  simulation improvements that reduce or address the sim2real gap - Define data collection and curation pipelines for incorporating real data in policy training - Design experiments focused on continuous performance and robustness improvements. - Explore the usage of adaptive and online reinforcement learning in deployed systems - Provide mentorship and supervision for junior team members, interns, and students. System Integration - Integrate learned components into a larger software stack - Collaborate with excavation and motion planning engineers - Build tools for analysing and evaluating the behavior of learned components ## What we’re looking for We recognize that excellent candidates come from diverse backgrounds with various combinations of skills. If you meet most of the core qualifications below, we highly encourage you to apply. Core qualifications - 2–5 years industry experience developing Reinforcement learning systems for control and/or planning and deploying them on real robots with a customer. If you only have experience with simulation, you’re most likely not a good fit for this position. - Experience with GPU accelerated simulation environments (e.g. IsaacSim/IsaacLab, CARLA, MuJoCo) - Strong Python skills and experience with PyTorch or similar libraries - Proficiency in C++ - Comfortable debugging real-world system behavior - Ability and willingness to travel as required by business projects. Great-to-Have Skills & Experience - ## Experience with hydraulic machinery - ## Experience with supervised learning or imitation learning - Research experience in reinforcement learning - Experience deploying robotic systems at scale (e.g. hundreds of units) - Familiarity with ROS or similar robotics frameworks - Experience with feature-flagged deployments, staged rollouts, or long-lived platforms - ## Experience with data curation for ML applications - Experience guiding, mentoring, or leading junior colleagues, students, or project teams. - Familiarity with or interest in utilizing AI coding tools. This Role is a Great Fit If - You are passionate about building systems that work reliably in the real world - You want to help build a long-lived excavation planning and control system intended to scale and positively impact the entire construction industry. - You are comfortable working with the realities of imperfect data and noisy measurements. - You have a keen interest in bridging the sim2real gap and understanding the differences between simulation and physical environments. - You are excited to help drive technical direction in a growing team transitioning from prototyping to the product stage. - You value a collaborative team culture rooted in thoughtful design, creative thinking, mutual respect, and pragmatism. ## About Gravis Robotics ## Company Overview - **One-liner**: Gravis Robotics retrofits earthmoving machines with plug-and-play autonomy to enable safer, more productive, and predictable construction sites. - **Entity Type**: Private – Series A-II - **Headquarters**: Zurich, Switzerland (also offices in Austin, Texas, USA and Oxford, UK) - **Founded**: 2022 - **Founders**: Ryan Luke Johns, Hanspeter Fässler, Simon Kerscher, Burak Çizmeci, Marco Hutter ## Core Business - **Primary industry**: Automation Machinery Manufacturing / Construction Robotics - **Target customers**: B2B – heavy civil construction firms, earthwork contractors, and equipment rental companies - **Mission**: To turn any earthmoving machine into a robot, augmenting human crews with superhuman productivity, safety, and predictability. ## Products & Services - **[Gravis RACK]**: A hardware-and-software retrofit kit (sensors, control unit, intuitive touchscreen) that transforms standard excavators into autonomous or teleoperated machines. Includes features like terrain-aware excavation (30% throughput improvement), autonomous maneuvers, self-stabilization, and augmented vision. (Type: Hardware + SaaS) - **[Teleoperation Tools]**: Advanced remote control capabilities enabling operators to manage machines from outside the cab, reducing exposure to hazards. - **[Deployment & Integration]**: Full support for integrating the Gravis RACK onto existing fleet machines, with site‑setup and task management via a simple interface. ## Market Standing - **Valuation / Funding**: Total funding of **$227.58M** as of August 2026, including a recent **$200M Series A** led by SoftBank Investment Advisers (announced August 20, 2026). Prior rounds included a seed round led by IQ Capital and Zacua Ventures. *Note: Some earlier profiles list $23M total funding – this appears to be outdated data before the Series A.* - **Key Metric**: Annual Revenue not publicly disclosed; headcount of **57 employees** (51-200 range) with **+43.5% YoY growth**. - **Notable Investors / Partners**: SoftBank Group, Armada Investment Group, Sunna Ventures, Imad Ventures, IQ Capital, Zacua Ventures. Deployment partnerships include DEVELON Europe, AG für Baumaschinen Schmerikon, and KIBAG. - **Growth Signals**: Handed over first commercial autonomous excavator to KIBAG in April 2026; expanding from Zurich hub into Austin and Oxford; active jobsite deployments; Inc. Magazine feature on Series A. ## Competitive Advantages - **Deep tech moat**: Core technology spun out from ETH Zurich’s Robotic Systems Lab, with over a decade of research in legged and autonomous systems applied to heavy machinery. - **Plug‑and‑play retrofit**: Works on existing machine brands (e.g., Develon) without requiring OEM redesign, enabling rapid fleet conversion. - **Field‑proven reliability**: Operates in extreme, unstructured outdoor environments (dirt, mud, slopes) where other autonomous systems struggle. - **Full‑stack approach**: Integrates hardware (RACK), perception, planning, teleoperation, and fleet management into a single cohesive product. ## Strategic Focus - **Scale deployment**: Use the $200M Series A to accelerate production of the Gravis RACK, expand into new geographic markets (US, UK), and grow the engineering and field operations teams. - **Product roadmap**: Improve autonomy level (e.g., full excavation without human input), expand to other earthmoving machine types (dozers, loaders), and deepen machine learning for terrain modeling. - **Talent acquisition**: Aggressively hiring across autonomy, SLAM, systems engineering, field robotics, and infrastructure roles (8 open positions as of September 2026). ## Why Work Here - **Culture**: Rated **4.6/5.0** on employer reviews (5 reviews) with strong scores in Work-Life Balance (4.3), Culture (4.5), and Career Growth (4.5). Described as a team of “great engineers, creative minds, and awesome people.” - **Work Policy**: Hybrid and on-site roles depending on location: Zurich (mostly on-site/hybrid), Austin (on-site), Oxford (hybrid). Internships are on-site in Zurich. - **Engineering culture**: Heavy emphasis on robotics, simulation, ML, and real‑world systems. Tech stack includes ROS, PyTorch, TensorFlow, Unreal Engine, SolidWorks, C++, Python, and more. Team includes alumni from ETH Zurich, NASA JPL, ANYbotics, and other top robotics groups. - **Perks**: Work on physical AI that has a tangible impact on global infrastructure; see your code move dirt on real construction sites; small, fast‑moving team with direct access to founders. ## Sources 1. [gravisrobotics.com](https://www.gravisrobotics.com/) 2. [jobs.lever.co/gravisrobotics](https://jobs.lever.co/gravisrobotics) 3. [linkedin.com/company/gravisrobotics](https://linkedin.com/company/gravisrobotics) 4. [cbinsights.com/company/gravis-robotics](https://www.cbinsights.com/company/gravis-robotics) ## Other roles at Gravis Robotics - [Senior Embedded Linux Engineer](https://feeny.ai/job/senior-embedded-linux-engineer-gravis-robotics-zurich-b49gfv526hs9) — Zurich, Switzerland - [Network Systems Engineer](https://feeny.ai/job/network-systems-engineer-gravis-robotics-zurich-zf0n4yx71x7w) — Zurich, Switzerland - [Technical Program Manager](https://feeny.ai/job/technical-program-manager-gravis-robotics-zurich-rv0154zc18v6) — Zurich, Switzerland - [Senior Platform Engineer - Infrastructure](https://feeny.ai/job/senior-platform-engineer-infrastructure-gravis-robotics-zurich-1g4nkg856mtv) — Zurich, Switzerland - [General Application Inquiry](https://feeny.ai/job/general-application-inquiry-gravis-robotics-zurich-zkm9ns5bj6na) — Zurich, Switzerland - [Field Robotics Engineer](https://feeny.ai/job/field-robotics-engineer-gravis-robotics-oxford-f885hvyejhtr) — Oxford - [Field Robotics Engineer - US](https://feeny.ai/job/field-robotics-engineer-us-gravis-robotics-austin-t1m3yv52dsgj) — Austin, TX - [Robotics Software Engineer Internship - Autonomy](https://feeny.ai/job/robotics-software-engineer-internship-autonomy-gravis-robotics-zurich-36wkbpdhr6cg) — Zurich, Switzerland - [Senior Reinforcement Learning Engineer](https://feeny.ai/job/senior-reinforcement-learning-engineer-apptronik-sunnyvale-5w6gnvcpryef) — Sunnyvale, CA - [Senior Reinforcement Learning Engineer](https://feeny.ai/job/senior-reinforcement-learning-engineer-apptronik-austin-sf7s6fbq2n5q) — Austin, TX