Senior ML Engineer (Energy & Utilities)

Department: Engineering

Location: Seattle

Compensation: $140K – $230K • Offers Equity • Offers Bonus

Employment Type: FullTime

About AZX

Our mission is to accelerate positive impact in critical industries through AI transformation. We specialize in physics-informed ML and enterprise AI solutions that directly address climate and sustainability challenges.

We’re growing quickly and already work with category-leaders in real estate (CBRE), energy (LevelTen Energy), logistics (Flexe) and utilities.

We bootstrapped profitably for our first year and are now backed by leading investors focused on AI, climate and energy.

We work on challenges in clean energy, decarbonization, climate risk, energy systems, and global economics. We’re building our company for long-term success and aim to create the ultimate place to work for those passionate about AI and making a positive impact.

About This Role:

We are seeking a Senior ML Engineer that will build the AI models and underlying tools that power AZX's work with utility clients — reusable capabilities used across many client engagements. Underneath the models, you'll also build the infrastructure that makes them possible: a fast building-energy simulation engine, tools for reading real-time grid sensor data, and utilities for working with standardized building data formats — much of which we publish as open source, so some of the people using your work are outside engineers you'll never meet. Rather than being assigned to one client account, you'll build the capabilities that every client-facing team draws on, and you'll join a specific project when your tools meet real-world data and need to be adjusted based on what actually happens in the field.

Responsibilities:

• Own the reusable utility ML libraries — forecasting, disaggregation, demand response, detection, and asset health — each shipped with its own evaluation harness and documentation.

• Build capabilities once as tested libraries with validation harnesses, so client pods deploy proven components (like meter disaggregation or load forecasting with abstention and monitoring built in) instead of reinventing them per engagement.

• Own the simulation engine — Rust crates and Python bindings — including its validation methodology against the reference oracle and its performance, and use it to make city-scale building stock tractable through representative-archetype simulation.

• Own the grid-data toolkits: protocol codecs (IEEE C37.118-class), synthetic scenario generators, and verification utilities, including generating synthetic-but-believable meter data calibrated until domain experts can't tell.

• Build the planning and dispatch support behind demand-response programs, where acting on a wrong number carries real cost.

• Own the publish path — versioned crates and Python packages — shipped with the evidence (evals, benchmarks) attached.

• Own the feedback loop with client pods: track what the capability got wrong in the field, and turn that into what you build next.

Core Qualifications:

• 5+ years of shipping applied ML on real-world signals — forecasting, disaggregation, detection/classification on interval or sensor data, survival/reliability modeling, or an adjacent-industry equivalent

• Strong numerical and scientific computing skills: feature engineering from raw interval data, solver-level numerics when needed, and a healthy distrust of your own metrics.

• Python plus a systems language — the models and tooling are Python, the engine is Rust; depth in one, working ability in the other, and the appetite to close the gap (Rust is teachable here; modeling judgment isn't).

• Library craft: you build things other engineers consume — versioned, tested, documented, with an API you'd want to call yourself.

• Willingness to do your own data engineering — finding, cleaning, joining, and profiling inputs yourself rather than trusting a prepared dataset.

• Practical fluency in our core stack — Python 3.12+ (numpy, pandas/polars, scikit-learn, statsmodels), time-series feature engineering, forecasting/clustering libraries (sktime/statsforecast-class), and SQL/Postgres or TimescaleDB-class hypertables.

• Comfort picking up Rust (or a comparable systems language) via PyO3/maturin, and building evaluation harnesses and CI for scientific software.

• Willingness to ramp quickly on energy-domain vocabulary if you don't already have it

• Bachelor's Degree; Master's is a plus

Why AZX!

• Be part of a fast-growing, profitable, mission-driven company with industry-leading clients tackling the massive opportunity of AI transformation in critical industries.

• Competitive early-stage startup compensation (based on capabilities, experience, and location)

• Bonus eligibility

• Health insurance with meaningful coverage for dependents

• Flexible paid time off

• Equity

• Fully remote culture with a cluster of teammates in Seattle

Additional Information:

• Must be able to travel 2x/year for company summits

• Applicants must be currently authorized to work in the United States on a full-time basis.

• We are unable to sponsor or take over sponsorship of employment visas at this time.

• Please note that our interview process includes a written take-home assignment followed by a live two-hour technical session with our engineering team, so if that format isn't a good fit, we'd ask that you not apply

• Please only apply to a maximum of 2 roles at a time, any applicants who apply to more then 2 roles within a 6 month period will automatically be disqualified

Next Steps:

If this job sounds like a great fit but you don’t check ALL of these qualification boxes, we’d still love to hear from you!