Senior ML Inference Engineer - Custom Hardware, LLMs

Socket.dev; Cupertino (CA); On-site; USD 193,000 - 262,000; Full time

Job summary

Amazon in Cupertino, CA is seeking a Senior Software Development Engineer to own design and implementation of inference data plane for large models on custom hardware, covering model execution, memory management, data movement, and serving integration. You will write and optimize low-level code, validate architectures end-to-end, build profiling tools, drive performance, and contribute to CI/CD.

Requires 7+ years of software development, strong C/C++, Linux, and experience with GPUs or

Qualifications

• 7+ years of full software development life cycle experience.
• Strong proficiency in C/C++.
• Strong Linux systems knowledge.
• Experience developing compute kernels for GPUs, DSPs, or custom accelerators.
• Proven track record of owning and delivering complex software features end-to-end.

Responsibilities

• Develop and optimize compute kernels for a custom ML accelerator architecture, targeting production-level performance for large language model inference.
• Implement and validate LLM architectures end-to-end - from PyTorch model definition through distributed execution on custom hardware.
• Integrate custom accelerator backends into open-source ML serving frameworks (vLLM, PyTorch), including scheduler extensions, memory management, and model parallelism.
• Build and maintain test infrastructure for model correctness validation across CPU, GPU, simulator, and hardware targets.
• Profile and optimize inference workloads - identify bottlenecks, instrument critical paths, and drive latency and throughput improvements from simulation through hardware bringup.
• Own features end-to-end: from design through implementation, testing, and integration into the broader software stack.
• Contribute to CI/CD pipelines that gate model and kernel changes on correctness and performance regressions.
• Mentor engineers, drive design reviews, and raise the engineering bar across the team.

Skills

C/C++

Linux

Compute kernels

LLM basics

Education

Bachelor's degree in computer science

Tools

PyTorch

vLLM

JAX

TensorRT

Job description

Amazon in Cupertino, CA is seeking a Senior Software Development Engineer to own design and implementation of inference data plane for large models on custom hardware, covering model execution, memory management, data movement, and serving integration. You will write and optimize low-level code, validate architectures end-to-end, build profiling tools, drive performance, and contribute to CI/CD.

Requires 7+ years of software development, strong C/C++, Linux, and experience with GPUs or