1 day ago
Base Salary
$168k - $227k/yr
Responsibilities
- Design and implement kernel-level optimizations and inference pipeline improvements for LLM serving workloads.
- Profile, benchmark, and tune model inference performance across CPU, GPU, Inferentia, and software stacks.
- Write maintainable software, participate in code reviews, mentor newer engineers, and provide peer feedback.
- Collaborate with applied scientists, ML engineers, and infrastructure teams to translate model requirements into production inference solutions.
- Evaluate emerging inference tools, frameworks, and Generative AI techniques and recommend improvements.
- Help establish technical vision, shape product strategy, and build scalable ML platform services.
Requirements
- 5+ years of non-internship professional software development experience.
- 5+ years of programming experience with at least one software programming language.
- 5+ years of leading design or architecture for new and existing systems, including reliability and scaling.
- Experience as a mentor, tech lead, or engineering team leader.
- Preferred: 5+ years of full software development lifecycle experience, including coding standards, code reviews, source control, build processes, testing, and operations.
- Preferred: experience with CUDA kernels or ML and low-level kernels.
- Preferred: experience optimizing LLM inference and serving, including CUDA kernel tuning, latency and throughput tuning, profiling, benchmarking, disaggregated serving, and KV caching.
Benefits
- Comprehensive health insurance, including medical, dental, vision, prescription, Basic Life and AD&D insurance, and optional supplemental life plans.
- Employee assistance program, mental health support, medical advice line, flexible spending accounts, and adoption and surrogacy reimbursement coverage.
- 401(k) matching, paid time off, and parental leave.
- Position is based in Bellevue, Washington, USA.
- Additional package components include sign-on payments and restricted stock units; compensation details are excluded here.
Tech Stack
Categories
About Amazon
Amazon builds and operates a global e-commerce marketplace, logistics network, and consumer devices, and provides cloud computing via AWS for businesses and developers. The company earns revenue from online retail, third‑party seller services, subscriptions like Prime, advertising, and AWS usage. Founded in 1994 and headquartered in Seattle, it is publicly traded on NASDAQ (AMZN) and serves customers in dozens of countries.