Paradigm Nat'l · 2 weeks ago
On Device ML Power and Performance Optimization Engineer
SD Metro Area
Full-time
Onsite
Entry, Mid Level
$120K/yr - $150K/yr
2+ years expParadigm Nat'l is seeking a talented Software/ML Engineer to join their Wearable System Architecture team, focusing on power and performance optimization for on-device machine learning. In this role, you will define, analyze, and optimize ML workloads to ensure efficient deployment across heterogeneous computing platforms within wearable devices.
Staffing & Recruiting
Hiring Manager
Tim Warren
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
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. For this, the candidate needs to able to compile an existing ML model against different ML accelerators using corresponding ML compilers. The candidate also needs to be familiar with RTOS and Android development and run-time environments
Analyze above results to reveal PnP (Power and Performance) characterization of different ML accelerators. This will eventually lead to the workload partition definition, i.e., which type of ML workload will be more suitable on which ML accelerators
Modify ML benchmark models by varying different key ML model parameters. For example: o Increase # of MACs significantly while keeping memory throughput relatively steady or vice-versa. For this, the candidate needs to able to modify an existing ML model by changing model parameters (e.g., increasing dimension of CNN layer) or model architecture (e.g., add a Fully Connected layer)
Analyze above results in order to reveal the relationship between key ML model parameters (e.g., # of MACs) and PnP metrics. This will eventually lead to PnP guideline that can help project PnP metrics based on values of key ML model parameters
Collect power and performance traces of AI driven use cases and identify areas of optimization
Qualification
Required
BS in Computer Science or Computer Engineering
2+ consumer product (e.g. Phone, Watch, Glass or other) experience
Familiar with RTOS, Android and embedded development environment
Familiar with ML development environment
The ideal candidate shall have strong firmware skills and will implement tiny ML on hardware/MCUs
This will require the candidate having skills to port and compile ML models to run on device
Company
Paradigm Nat'l
At our skilled IT staffing and recruiting agency, we place a strong emphasis on fostering genuine relationships between employees and employers.
2-10 employees
Funding
Current Stage
Early StageLeadership Team
Scott Pollard
Managing Partner
Tim Warren
Managing Partner
Company data provided by crunchbase