On Device ML Power and Performance Optimization Engineer

Paradigm Nat'l; United States; On-site; USD 140,000 - 170,000; Full time

Benefits offered by this job

Medical insurance

Vision insurance

401(k)

Paid maternity leave

Paid paternity leave

Job summary

A technology company in the United States is looking for a Mid-Senior Level On Device ML Power and Performance Optimization Engineer. In this full-time role, you will work on optimizing machine learning workloads for wearable devices. Responsibilities include defining workload strategies and analyzing performance across various computing platforms. An educational background in Computer Science or Computer Engineering is required, along with experience in embedded systems and machine learning.

Qualifications

• 2+ years of experience with consumer products (e.g., Phone, Watch, Glass).
• Strong firmware skills for implementing tiny ML on hardware/MCUs.
• Ability to port and compile ML models for PnP metrics analysis.

Responsibilities

• Define ML workload partitioning strategies for accelerators.
• Develop guidelines for ML model architectural exploration.
• Execute ML benchmarks under various configurations.

Skills

Power and performance optimization

ML workload partitioning

Embedded development

Firmware skills

ML model compilation

Cross-functional collaboration

Education

BS in Computer Science or Computer Engineering

Tools

RTOS

Android development

Embedded development environment

ML development environment

Job description

On Device ML Power and Performance Optimization Engineer

This range is provided by Paradigm Nat’l. Your actual pay will be based on your skills and experience — talk with your recruiter to learn more.

Base pay range

$140,000.00/yr - $170,000.00/yr

Direct message the job poster from Paradigm Nat’l

JOB OVERVIEW

We are seeking a talented Software/ML Engineer to join our Wearable System Architecture team, focusing on power and performance optimization for on-device machine learning.

In this role, you will work on defining, analyzing, and optimizing ML workloads to ensure efficient deployment across heterogeneous computing platforms within wearable devices. You will collaborate closely with cross‑functional engineering teams under the guidance of the Wearable System Architects.

Key Responsibilities

• Define ML workload partitioning strategies based on detailed power and performance (PnP) characterization of ML accelerators.
• Develop and document PnP guidelines to support ML model architectural exploration and optimization.
• Drive end-to-end power and performance optimization of AI-driven use cases, from model design through deployment on device.

This position offers the opportunity to work at the intersection of machine learning, systems architecture, and hardware optimization, shaping the efficiency and capability of next‑generation wearable AI experiences.

Additional Responsibilities

• Collect power and performance measurement results and traces of ML benchmarks (e.g., MLPerf‑Tiny).
• Execute ML benchmarks under different on-device configurations, for example: Execute ML benchmark on different on device ML accelerators.
• Execute ML benchmark on slow/external memory and fast/internal memory. Compile an existing ML model against different ML accelerators using corresponding ML compilers; familiar with RTOS, Android development, and run‑time environments.
• Analyze results to reveal PnP characterization of different ML accelerators, leading to workload partition definition.
• Modify ML benchmark models by varying key ML model parameters (e.g., increase # of MACs while keeping memory throughput steady) to derive PnP guidelines.
• Collect power and performance traces of AI‑driven use cases and identify optimization areas.

QUALIFICATIONS

• BS in Computer Science or Computer Engineering
• 2+ consumer product (e.g., Phone, Watch, Glass) experience
• Familiar with RTOS, Android, and embedded development environment
• Familiar with ML development environment
• Strong firmware skills and experience implementing tiny ML on hardware/MCUs
• Skills to port and compile ML models to run on device; modify ML models for PnP metrics analysis

Seniority level

Mid‑Senior level

Employment type

Full‑time

Job function

Information Technology

Benefits

• Medical insurance
• Vision insurance
• 401(k)
• Paid maternity leave
• Paid paternity leave