Senior Engineer Edge AI Infrastructure & Tooling , Device OS

Are you passionate about bringing state of the art AI technology to edge devices Join Amazons Device OS organization where were revolutionizing how AI powers everyday devices. Were seeking exceptional Senior Software Development Engineers who can help us push the boundaries of edge computing and artificial intelligence. This is your chance to shape the future of AI-enabled devices that impact millions of customers worldwide.


Key job responsibilities
As a Sr. Software Development Engineer you will conceive design and deliver innovative features for Amazon devices. You will be responsible for architecting and developing software solutions for new and innovative products.

Investigate and prototype edge computing solutions with AI integration capabilities
Develop backend integrations for various SoC vendors and AI accelerators
Build developer tools including profilers debuggers model converters and bench marking suites
Optimize model deployment workflows and performance for resource-constrained environments
Create SDKs APIs and documentation to enable seamless developer experiences
Create automated testing frameworks for model accuracy and performance validation
Collaborate with ML researchers to bridge the gap between research and production
Work in an Agile/Scrum environment to deliver high quality software
Establish architectural principles and mentor team members

About the team
The Device OS Team builds Edge AI/ML frameworks enabling partners to launch applications services and devices customers love. We develop unified inference platforms that connect advanced AI models with diverse hardware ecosystems across multiple SoC platforms. Our infrastructure and tooling empower developers to deploy optimize and monitor high-performance AI models on edge devices.


- 5 years of non-internship professional software development experience
- Experience in embedded development in C/C
- 5 years of leading design or architecture (design patterns reliability and scaling) of new and existing systems experience
- Experience in state-of-the-art deep learning models architecture design and deep learning training and optimization and model pruning
- 5 years in ML tooling and dev/prod infrastructure
- Proven experience working with edge hardware platforms (Qualcomm MediaTek NVIDIA Jetson Apple Neural Engine etc)
- Experience with edge AI inference frameworks (PyTorch ExecuTorch TensorFlow Lite ONNX Runtime etc.)
- Proficiency with model optimization techniques: quantization (INT8 FP16 mixed-precision) pruning knowledge distillation
- Experience with model formats (.tflite .onnx .pt .trt FlatBuffers) and conversion pipelines
- Experience deploying and tuning LLMs using techniques like LoRA QLoRA and instruction tuning
- Strong coding skills with the ability to implement custom optimized kernels

- 5 years of full software development life cycle including coding standards code reviews source control management build processes testing and operations experience
- Experience deploying LLMs or advanced ML models on resource-constrained devices
- Experience with MLOps practices automated model testing model production (deployment CI/CD monitoring) and operationalizing LLMS & ML models at scale
- Familiarity with heterogeneous computing and workload scheduling across CPU/GPU/NPU
- Experience with real-time systems latency-critical applications and deterministic inference
- Background in SDK development developer tooling and creating exceptional developer experiences
- Virtual platform development and cloud deployment
- Strong cross-functional leadership with the ability to influence product roadmaps and technical strategy across organizations

Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace accommodation or adjustment during the application and hiring process including support for the interview or onboarding process please visit for more information. If the country/region youre applying in isnt listed please contact your Recruiting Partner.