AI Battery Health Estimation Engineer

Celtrix AI

Remote · $160k – $200k / year · Full-time · Posted 4 weeks ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

Every one of the 1.2 million devices running our firmware will lean on the model you build to tell its owner how much battery life is really left. Celtrix AI ships on-device intelligence for wearables and industrial sensors, and today our state-of-health estimates drift badly after a few hundred charge cycles. This role owns the fix end to end: modelling cell degradation from voltage, temperature and current traces, compressing the result so it fits within a few kilobytes of flash, and proving accuracy against our lab cycling rigs. You'll sit with two firmware engineers and one electrochemist, and you'll be the person who decides what goes into the next quarterly firmware release.

Responsibilities

Own the battery state-of-health model from raw cycler data to the quantized artifact we flash on devices
Design features that survive noisy field telemetry, partial charges and extreme temperatures
Partner with firmware to keep inference under 2 ms on Cortex-M class microcontrollers
Set up lab-versus-field validation dashboards that the hardware team reviews every release

Requirements

Strong background modelling physical or electrochemical time-series data
Hands-on experience shrinking models for constrained hardware (quantization, pruning, distillation)
Comfortable reading battery datasheets and talking with hardware engineers
Fluent Python and PyTorch; MLflow or similar experiment tracking