ML Runtime Optimization Engineer
Applied Compute · Sunnyvale
Infrastructureonsitemid-level$215k–$315k
At a glance
Highlights
- Optimize ML inference latency and efficiency for on-road and off-road ADAS stacks.
- Deploy pruned and quantized models to memory-constrained embedded platforms.
- Profile model performance to find bottlenecks in stack integration.
What they offer
- Equity
- Health insurance
- Dental insurance
- Vision insurance
- Life and disability insurance
- 401(k) with employer match
- Learning stipend
- Wellness stipend
- Paid time off
Ideal candidate
An embedded-minded ML engineer who loves squeezing maximum performance from constrained hardware and partnering closely with autonomy teams to ship real-time systems.
Requirements
- Bachelor's in Electrical Engineering, Computer Science, Mathematics, Physics or related field
- 3+ years of experience with ML accelerators, GPU, CPU, SoC architecture and micro-architecture
- Strong software development skills with focus on embedded programming
- Experience profiling and optimizing model performance on embedded compute platforms
- Experience working with deep learning frameworks such as PyTorch, JAX and ONNX
- remote policy
- In-office 5 days a week with occasional remote flexibility
Lab profile
About Applied Compute
Powering physical AI with digital infrastructure, operating systems, and autonomy for moving machines.
What they build
- Tools and infrastructure
- Operating systems
- Autonomy
Known for
- Physical AI infrastructure
- Machine learning behavior and planning
- Embedded Core OS and firmware
- Autonomy for automotive and defense
Key facts
- Founded in 2017
- Based in Silicon Valley
- Valued at $15 billion
Posted · Last seen