Sr. Software Development Engineer, FAR (Frontier AI & Robotics)

Amazon; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Join a pioneering team in robotics and AI, where you'll optimize cutting-edge models and work alongside leading experts. This role focuses on transforming innovative research into high-performance systems, leveraging your expertise in CUDA and TensorRT. You'll balance deep technical work with strategic input on model architectures, ensuring that robotics solutions are designed for performance from the ground up. Be part of a dynamic environment that pushes the boundaries of what's possible in intelligent robotics, with your contributions making a real impact at scale.

Qualifications

• 5+ years of software development experience with strong Python and C++ skills.
• Experience with ML optimization frameworks like TensorRT and ONNX Runtime.

Responsibilities

• Drive strategies for optimizing large-scale foundation models using TensorRT and CUDA.
• Collaborate with scientists to influence model architecture for optimal performance.

Skills

Python

C++

CUDA

Machine Learning Optimization

Software Development

Design Patterns

Performance Profiling

Education

Bachelor's degree in Computer Science

Tools

TensorRT

NVIDIA ML Stack

ONNX Runtime

CUDA Graph

Job description

Sr. Software Development Engineer, FAR (Frontier AI & Robotics)

Job ID: 2914307 | Amazon.com Services LLC

Join the next revolution in robotics at Amazon's Frontier AI & Robotics team, where you'll work alongside world-renowned AI pioneers like Pieter Abbeel, Rocky Duan, and Peter Chen to make breakthrough foundation models run at production scale. As a Senior Machine Learning Engineer embedded in our science team, you'll be instrumental in transforming cutting-edge research into high-performance production systems. You'll collaborate directly with scientists to optimize large-scale transformer architectures for robotics applications, leveraging your expertise in CUDA and TensorRT to achieve unprecedented inference efficiency at Amazon scale.
In this role, you'll balance deep technical optimization work with strategic input on model architecture decisions, ensuring our innovative robotics models are designed with performance in mind from the ground up. You'll leverage NVIDIA's acceleration stack and other compilation techniques to tackle ambitious performance targets, working at the intersection of large language models and real-world robotics applications.

Key job responsibilities

1. Drive inference optimization strategies for large-scale foundation models using TensorRT, CUDA, and other NVIDIA tools
2. Collaborate closely with scientists to influence model architectures for optimal hardware utilization
3. Design and implement efficient compilation pipelines for complex transformer architectures
4. Develop comprehensive benchmarking frameworks to measure and optimize model performance
5. Build robust monitoring solutions to ensure reliable model serving at scale
6. Explore and evaluate emerging optimization techniques including ONNX Runtime and other ML compilers
7. Maintain high engineering standards through proper testing, documentation, and code review practices

A day in the life

1. Optimize transformer blocks using custom CUDA kernels and TensorRT optimization techniques
2. Partner with scientists to analyze model architectures and propose efficiency improvements
3. Implement and benchmark various optimization strategies for large-scale models
4. Debug performance bottlenecks using NVIDIA profiling tools
5. Participate in technical discussions about new model architectures with the science team
6. Design and maintain performance monitoring systems for production deployment
7. Prototype new acceleration approaches using emerging compilation frameworks

About the team

At Frontier AI & Robotics, we're not just advancing robotics – we're reimagining it from the ground up. Our team, led by pioneering AI researchers Pieter Abbeel, Rocky Duan, and Peter Chen, is building the future of intelligent robotics through groundbreaking foundation models and end-to-end learned systems. We tackle some of the most challenging problems in AI and robotics, from developing sophisticated perception systems to creating adaptive manipulation strategies that work in complex, real-world scenarios. What sets us apart is our unique combination of ambitious research vision and practical impact. We leverage Amazon's massive computational infrastructure and rich real-world datasets to train and deploy state-of-the-art foundation models. Our work spans the full spectrum of robotics intelligence – from multimodal perception using images, videos, and sensor data, to sophisticated manipulation strategies that can handle diverse real-world scenarios. We're building systems that don't just work in the lab, but scale to meet the demands of Amazon's global operations. Join us if you're excited about pushing the boundaries of what's possible in robotics, working with world-class researchers, and seeing your innovations deployed at unprecedented scale.

BASIC QUALIFICATIONS

- Bachelor's degree in computer science or equivalent
- 5+ years of non-internship professional software development experience
- 5+ years of programming with at least one software programming language experience
- 5+ years of leading design or architecture (design patterns, reliability and scaling) of new and existing systems experience
- Experience as a mentor, tech lead or leading an engineering team
- Strong expertise in Python, C++ and CUDA programming
- Experience with TensorRT or similar ML optimization frameworks
- Track record of optimizing ML models for production

PREFERRED QUALIFICATIONS

- Expertise in NVIDIA's ML stack (cuDNN, CUDA Graph, etc.)
- Experience with ML compilers (ONNX Runtime, TVM, etc.)
- Experience with transformer model optimization
- Background in performance profiling and optimization
- Experience working directly with research teams
- Track record of building robust monitoring systems
- Experience with large-scale ML serving systems