Senior AI Robotics Software Engineer

Amaru Robotics; Mountain View (CA); Vor Ort; USD 150.000 - 280.000; Vollzeit

Benefits dieser Stelle

Equity

Zusammenfassung

Amaru Robotics in Mountain View, CA seeks a senior engineer to train modern manipulation policies and make them work reliably in real-world robotic packing tasks. This software + AI role focuses on building and deploying ML-powered robotics software for e-commerce warehouses.

You will own the data loop from live robot data collection to training, evaluation, and deployment, working on perception and control in production. Position requires 4–5 days/week on-site and occasional travel.

Qualifikationen

• Senior-level robotics/ML software experience (3–5+ years).
• Hands-on deployment on real robots in commercial/industrial settings.
• Fluency with modern manipulation and computer-vision methods; agentic coding.

Aufgaben

• Train and deploy manipulation policies (imitation learning, visuo-motor policies, RL) for dual-arm packing.
• Build and improve the perception stack — detection, segmentation, and pick-and-place reliability in production.
• Own the data collection → training → evaluation → deployment loop.
• Deploy on-site with us (light travel ~10–20%, on-call) and ensure reliability in live customer facilities.
• Work in person (4-5 days/week) in Mountain View, CA

Kenntnisse

Python

Robotics software

ML/AI

Hands-on deployment

Tools

Claude Code

Codex

Jobbeschreibung

Amaru builds AI-powered robotic packing cells for e-commerce warehouses. Packing is the last major step in fulfillment still done entirely by hand — we automate the whole job (scan → pick → box or bag → weigh → tape → label) in a compact cell that drops into an existing packing station with zero IT integration.

We're a lean, second-time robotics team (Traptic → Bowery Farming; Zoox) with our first paying customer, robots heading to production, and backers who believe in us ($2M raised). Join early and your code runs in real warehouses, in front of customers, within weeks — not years.

We're hiring a senior engineer who can train modern manipulation policies and make them work reliably in the real world. This is a software + AI role.

What you'll do

• Train and deploy manipulation policies (imitation learning, visuo-motor policies, keypose prediction, RL, sim-to-real) for dual-arm packing.
• Build and improve the perception stack — detection, segmentation, and pick-and-place reliability in production.
• Own the loop from real-robot data collection → training → evaluation → deployment.
• Deploy on-site with us (light travel, ~10–20%, plus on-call) and use good judgment about what's reliable and performant in a live customer facility.
• Work in person (4-5 days/week) in Mountain View, CA

You have

• Senior-level experience (roughly 3–5+ years) building robotics or ML software; strong Python.
• Hands-on experience getting a robot working in a real commercial or industrial deployment — any robot (arms, drones, mobile), not just a lab or side project.
• Fluency with modern manipulation / computer-vision methods, and agentic coding (claude code/codex).

Nice to have

• Deployed learned policies or perception on real robots.
• Early-stage startup experience.

Compensation:

$150K–$280K base + meaningful early-stage equity.