Rhoda Ai
Software Engineer Intern, Inference
Mountain View. Posted 25 days ago
The role
You will work with infra and research engineers to make model inference faster and more efficient across the stack. You will own a scoped project from end to end and ship it into production or research workflows.
What you will do
- Profile and benchmark inference for large video and world models to find bottlenecks in latency, throughput, and memory.
- Apply and evaluate inference optimization techniques like quantization, low-precision inference, step distillation, sampling acceleration, attention and caching optimizations, model compilation, and g
- Make data movement and processing more efficient including video decoding, preprocessing, input pipelines, host–device transfer, caching, and storage/IO paths.
- Write and tune GPU kernels for performance-critical operators and integrate them into the inference stack.
- Build tooling and benchmarks to track performance regressions and improvements.
- Work with researchers to turn promising ideas into production-quality infrastructure.
Required qualifications
- Currently pursuing a BS, MS, or PhD in Computer Science, Electrical/Computer Engineering, or a related field.
- Strong programming skills in Python and/or C++.
- Solid understanding of deep learning fundamentals and at least one framework.
- Comfortable reading performance data and reasoning about trade-offs between latency, throughput, memory, and accuracy.
Nice to have
- Experience with video model inference is a huge plus
- Research experience in systems or ML
- Experience with real-time or latency-critical inference
- Experience with multi-GPU inference
- Contributions to open-source ML systems projects
- PyTorch preferred
Benefits
- A real project with measurable impact on robots operating in the real world.
- Mentorship from experienced infra and research engineers.
- Access to modern GPU compute for experiments.
About the company
Rhoda AI is building the next generation of generalist intelligent robots. They own the full robotics stack from hardware to foundation world models.