Robotics Software Engineer
Robotics Software Engineer, Embodied AIAbout Hivebotics Hivebotics is a robotics company building autonomous robots that operate in real commercial environments. We are growing our US team to build the learning stack that lets our robots pick up new manipulation skills from real-world data.
The Role:
You will own our learned manipulation capability end to end, focusing on grasping and contact-rich dexterous manipulation. You will take tasks from concept to policies running on real hardware. That covers collecting demonstration data, fine-tuning foundation models, deploying to the fleet, and validating performance in real-world conditions. You will need a strong foundation in robotics, manipulation, and control, solid programming ability, and a rigorous experimental mindset.
What You Will Do:
- Build the teleoperation and recording pipeline that turns real deployments into training data
- Fine-tune open-weight vision-language-action (VLA) base policies on our data using LoRA or equivalent methods, and build the evaluation harness to measure them
- Develop grasping and contact-rich manipulation policies and controllers, and validate them on real hardware
- Export policies to a portable runtime (ONNX or equivalent) and deliver them to the fleet deployment pipeline as versioned artifacts that can be rolled back
- Re-run base model selection on a regular schedule so we can adopt stronger foundation models as the field moves
- Document code, algorithms, experiments, and results clearly
What We Are Looking For:
- Degree in Robotics, Computer Science, Software Engineering, or a related field, or equivalent practical experience
- Hands-on experience with imitation learning from demonstrations
- Working knowledge of at least one current open VLA model family (e.g. OpenVLA, Octo, π0, GR00T)
- Experience exporting and deploying models through ONNX or an equivalent runtime
- Experience with GPU-accelerated simulation such as NVIDIA Isaac Sim or Isaac LabStrong Python skills and a solid grounding in manipulation and control
Nice to Have:
- Has shipped a learned policy onto real robot hardware
- Experience with multi-fingered end effectors or force/tactile sensingROS 2Experience with manipulation benchmarks such as LIBEROSimulation experience with Gazebo or MuJoCoCloud platforms (AWS, Azure, or GCP), Docker, Kubernetes, CI/CD, or MLOps practices
- Familiarity with LLM application architectures, orchestration, or agentic frameworks
- Comfortable working with AI-assisted coding tools
- Work Authorization
Candidates must be authorized to work in the US. We are unable to sponsor visas for this role.
Hivebotics is an equal opportunity employer. We do not discriminate on the basis of race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, veteran status, or any other legally protected status.