About the Role
The role involves enhancing the performance of machine learning models used in autonomous robots. Responsibilities include profiling, optimizing, and deploying models in production environments where low latency and high reliability are critical.
Responsibilities
- Profile and analyze machine learning model performance in production systems
- Optimize deep learning models for inference speed and resource efficiency
- Collaborate with research and robotics teams to integrate models into real-world applications
- Implement model compression techniques such as quantization and pruning
- Improve end-to-end latency of ML pipelines in edge environments
- Develop tools for monitoring and benchmarking model performance
- Work closely with infrastructure engineers to deploy optimized models
- Ensure scalability and reliability of ML systems in dynamic environments
- Debug performance bottlenecks across hardware and software layers
- Maintain clean, testable, and well-documented codebases
- Stay current with advancements in ML optimization and edge computing
- Support deployment of models on embedded and mobile platforms
- Evaluate trade-offs between accuracy, speed, and memory usage
- Contribute to version control and CI/CD workflows
- Assist in defining best practices for ML performance engineering
Nice to Have
- Master’s or PhD in Computer Science or related field
- Experience with ONNX or TensorRT for model optimization
- Background in real-time systems or embedded software
- Contributions to open-source ML or systems projects
- Published work in machine learning or systems conferences
Compensation
Competitive salary with equity and benefits
Work Arrangement
Hybrid
Team
Small, fast-moving team focused on robotics and AI infrastructure
What We Value
- Ownership of technical challenges from design to deployment
- Clear communication across technical and non-technical stakeholders
- Iterative development with measurable impact
- Curiosity and rigor in solving performance-critical problems
- Collaborative culture with a focus on learning and growth
Day in the Life
- Morning sync with robotics and ML teams to review performance metrics
- Profiling inference bottlenecks in simulation and real-world data
- Implementing optimization passes on trained models
- Testing changes on edge hardware for latency and accuracy
- Documenting findings and sharing with engineering teams
Available for qualified candidates
