Lead Data Scientist, Robotics

Agility Robotics Agility Robotics · Robotics · Remote · Software Engineering

Lead Data Scientist for Agility Robotics, focusing on transforming complex robot data (telemetry, logs, sensor streams) into insights and models to improve robot reliability, performance, and economics. The role involves predictive maintenance, fleet performance analysis, anomaly detection, and manufacturing quality feedback loops, aiming to build a data-driven engineering organization for their humanoid robots.

What you'd actually do

  1. Predictive maintenance & hardware reliability. Build models that predict MTBF and remaining useful life for specific components (actuators, cameras, compute, power systems). Partner with hardware engineering to model wear-and-tear under varying duty cycles, payloads, and environmental conditions, and turn those models into maintenance schedules and design feedback.
  2. Fleet performance & RaaS unit economics. Analyze telemetry and logs to find which software versions, site conditions, or usage patterns correlate with the highest failure and intervention rates. Work with Product to define the "golden signals" of a RaaS deployment and stand up the dashboards behind each. Quantify the cost of human intervention (teleop, on-site support, manual recovery) and its drivers.
  3. Root-cause & anomaly detection tooling. Build detection and RCA tooling that surfaces anomalies in fleet behavior early and helps engineers get from symptom to cause faster.
  4. Manufacturing quality & feedback loops. Join end-of-line test data with field performance to find which manufacturing signals predict early field failures, and close the loop back to the factory to catch defects before they ship

Skills

Required

  • Python
  • SQL
  • statistical modeling
  • reliability/survival analysis
  • time-series analysis
  • anomaly detection
  • predictive maintenance
  • causal/observational inference
  • technical leadership
  • mentoring

Nice to have

  • robotics
  • autonomous systems
  • hardware
  • IoT/connected devices
  • industrial
  • manufacturing
  • fleet operations
  • RaaS/subscription unit economics
  • SRE-style operational metrics
  • manufacturing quality systems
  • SPC
  • yield/defect analytics

What the JD emphasized

  • 10+ years applying data science / statistical modeling to real-world problems, with a track record of owning ambiguous, high-impact problems end to end.
  • Deep expertise in some combination of: reliability/survival analysis, time-series and anomaly detection, predictive maintenance, and causal/observational inference.
  • 3+ years serving as a technical lead or the senior-most IC on cross-functional efforts, with a track record of setting technical direction for a team of data scientists/analysts, mentoring and growing ICs, and driving alignment across engineering and business stakeholders without formal authority.

Other signals

  • define how we use data to build better robots
  • transform massive volumes of complex robot data into the insights and models that drive decisions
  • improve robot performance at scale
  • predictive maintenance & hardware reliability
  • fleet performance & RaaS unit economics
  • root-cause & anomaly detection tooling
  • manufacturing quality & feedback loops