Robotics Software Engineer

Hivebotics; San Francisco (CA); On-site; USD 150,000 - 230,000; Full time

Job summary

Hivebotics in the United States builds autonomous robots for real commercial environments and leads the learning stack to enable new manipulation skills from real-world data.

You will own the learned manipulation capability end to end, focusing on grasping and contact-rich dexterous manipulation, taking tasks from concept to policies running on real hardware with rigorous experimentation.

Qualifications

• Degree in Robotics, CS, Software Engineering or equivalent practical experience.
• Hands-on experience with imitation learning from demonstrations.
• Working knowledge of open VLA model families (e.g. OpenVLA, Octo, π0, GR00T).
• Experience exporting and deploying models through ONNX or equivalent runtime.
• Experience with GPU-accelerated simulation (NVIDIA Isaac Sim/Lab).
• Strong Python skills and grounding in manipulation and control.

Responsibilities

• Build teleoperation and recording pipelines turning real deployments into training data.
• Fine-tune open-weight VLA base policies on our data using LoRA; build evaluation harnesses.
• Develop grasping and contact-rich manipulation policies and controllers on real hardware.
• Export policies to a portable runtime (ONNX) and deliver them to fleet deployment as versioned artifacts.
• Re-run base model selection on a regular schedule to adopt stronger foundation models.
• Document code, algorithms, experiments, and results clearly.

Skills

Robotics

Imitation learning

Python

Control theory

Experimentation

Education

Bachelor's degree in Robotics or related field

Tools

ONNX

NVIDIA Isaac Sim

Isaac Lab

LoRA

Job description

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 Lab
• Strong 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 sensing
• Experience with manipulation benchmarks such as LIBERO
• Simulation experience with Gazebo or MuJoCo
• Cloud 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.