Staff Machine Learning Engineer, Time Series & Statistical Methods

Nominal•Los Angeles, CA

About The Position

As a Staff Machine Learning Engineer, Time Series & Statistical Methods, you'll give our agents real numerical tools, because LLMs alone can't reason well over millions of sensor samples, and you'll set Nominal's direction on ML for hardware data, from classical methods to deep learning. This role is part of the Hardware Intelligence team, which is responsible for Nominal's agents, AI-native applications, and MCP, and its forward-leaning AI bets. The team's mission is to unlock the bottlenecks of the hardware lifecycle with AI. Their agents reason over physical reality, from high-rate telemetry and test campaigns to designs and simulations, where real test results are the ground truth their work is checked against. The team believes opinionated AI, built for the real work of hardware programs, will change how the world engineers. They are collaborative, iterative, and high-agency, and they are human-centered and customer-focused. They build with the newest AI tools every day, and because those tools keep changing, so do they: they stay curious and keep looking for the better way. Their team spans data science and ML, distributed systems, search, and knowledge systems, and they obsess over how agents can be genuinely useful to the engineers who rely on them.

Requirements

8+ years in applied ML or statistics, with production systems on time-series or sensor data.
Deep classical grounding: statistics, signal processing, anomaly detection, and forecasting.
Hands-on deep learning: transformers, embeddings, and representation learning for sequences and sensor data.
Strong software engineering; your methods ship as reliable, tested code.
Judgment about simple-versus-complex: you know when a well-chosen statistical test beats a neural net, and when it doesn't.
A track record of setting technical direction across a team and raising the bar for the engineers around you.
You build with modern AI coding agents (Claude Code, Cursor, Codex) every day, and stay curious and open to better ways of working. The tools keep changing, and so do we.
Must be a (i) U.S. citizen or national, (ii) U.S. lawful, permanent resident (aka green card holder), (iii) Refugee under 8 U.S.C. § 1157, or (iv) Asylee under 8 U.S.C. § 1158, or be eligible to obtain the required authorizations from the U.S. Department of State.

Nice To Haves

You've built anomaly detection or forecasting that drove real operational decisions, in observability, predictive maintenance, or vehicle telemetry.
You've worked with telemetry from aircraft, vehicles, energy systems, or robots.
You've shipped ML methods as tools that other systems or agents call, not only as models.
You've worked with the latest models beyond text: VLMs, VLAs, multimodal transformers, or foundation models for robotics and physical systems.

Responsibilities

Build anomaly detection, change-point detection, and forecasting for high-rate test and fleet telemetry.
Package these methods as agent tools, so our agents can run real feature engineering and statistics instead of guessing.
Develop signal-processing and statistical methods (frequency analysis, trend fitting, run-to-run comparison) that hold up on noisy, real-world data.
Partner with evals to measure when a method is good enough to put in front of engineers.
Set the technical bar and roadmap for ML at Nominal, including when, and whether, to invest in learned models over classical ones.