On-Device Machine Learning Power and Performance Optimization Engineer
On-Device Machine Learning Power and Performance Optimization Engineer
Employer Active
Job Alert
You will be updated with latest job alerts via email
Share
Job Alert
You will be updated with latest job alerts via email
Not Disclosed
Salary Not Disclosed
1 Vacancy
Job Description
Cohesive Technologies is a global IT Services & Solutions company providing IT Staffing Services and Application Development Services necessary for technology leaders to deliver business value. We help our people and clients succeed by leveraging our expertise deep industry and market knowledge proprietary assessment tools and techniques and project delivery methodologies. Through relationships with thousands of specialized professionals we bring an unparalleled ability to match talent with opportunities by assessing recruiting developing and engaging the best and brightest people for our clients. We combine broad geographic presence worldclass solutions and a tailored consultative approach to help our people and clients achieve higher performance and outstanding results.
Position: OnDevice Machine Learning Power and Performance Optimization Engineer
Location: San Diego CA
- We are seeking a highly skilled Software/ML Engineer to join our Wearable Systems team in San Diego. This role involves power and performance optimization of ondevice machine learning for advanced consumer electronics in AR/VR and mixed reality devices. The ideal candidate will have expertise in embedded systems ML accelerators and model optimization. You will contribute to innovative AIdriven use cases ensuring power efficiency and performance excellence for wearable devices and IoT solutions.
Key Responsibilities:
Power and Performance Analysis:
- Collect and analyze power and performance measurement results of ML benchmarks (e.g. MLPerfTiny).
- Execute ML benchmarks on different ondevice configurations including accelerators memory types and runtime environments.
- Provide detailed Power and Performance (PnP) characterization of ML accelerators.
Workload Partitioning and Guidelines:
- Define ML workload partitioning based on PnP metrics.
- Establish clear PnP guidelines for ML model architectural exploration.
Model Modification and Optimization:
- Modify existing ML models to explore the relationship between model parameters (e.g. # of MACs memory throughput) and PnP metrics.
- Implement ML models on ARMbased MCUs and accelerators leveraging compilers like ARM Vela or equivalent.
- AI Use Case Optimization: o Collect power and performance traces for AIdriven use cases.
- Identify optimization opportunities and implement solutions to enhance performance and power efficiency.
CrossFunctional Collaboration:
- Work closely with system architects hardware engineers and software teams to deliver optimized solutions.
Minimum Qualifications:
- Bachelors degree in computer science Computer Engineering or related field.
- 2 years of experience with consumer products (e.g. phones watches glasses IoT devices).
- Experience with RTOS Android and embedded development environments.
- Familiarity with ML development tools and frameworks.
Preferred Qualifications:
- Masters degree in Computer Science Computer Engineering or related field with coursework in ML and computer architecture.
- 3 years of experience with consumer electronics development.
- Proficiency in ML frameworks such as PyTorch or TensorFlow.
- Handson experience with ML accelerators (e.g. ARM U55/U65/U85) and corresponding compilers (e.g. Vela Qualcomm AI SDK).
- Proven ability to instrument and profile ML execution analyze results and propose optimizations.
- Strong understanding of power measurement fundamentals and analysis techniques.
Personal characteristics:
- Team player
- Proactiveness in collaborating and execution.
- Flexibility to switch technical context
- Willingness to learn new methods / tools / processes
- Ability to prioritize and multitask
- Strong problem solving and critical thinking skills.
Cohesive Technologies is an equal access/equal opportunity employer and does not discriminate on the basis of age color disability marital status national origin race religion sex sexual orientation veteran status or any other classification prescribed by applicable law.
Employment Type
Full Time
