2 days ago
Bellevue, WA, USAMid Level
H1B sponsor
Base Salary
$144k - $194k/yr
Responsibilities
- Design and implement kernel-level optimizations and inference pipeline improvements for LLM serving.
- Profile, benchmark, and tune model inference performance across hardware and software stacks.
- Write maintainable software, participate in code reviews, mentor newer engineers, and document design decisions.
- Collaborate with applied scientists, ML engineers, and infrastructure teams on production inference solutions.
- Evaluate tools, frameworks, and generative AI techniques for inference optimization.
Requirements
- At least 3 years of non-internship professional software development experience.
- At least 2 years of non-internship design or architecture experience involving design patterns, reliability, and scaling.
- At least 1 year of software development engineer or related occupational experience.
- At least 1 year designing and developing large-scale, multi-tiered, multi-threaded, embedded, or distributed software using C#, C++, Java, or Perl.
- At least 1 year of object-oriented design experience.
- Bachelor's degree or foreign equivalent in Computer Science, Engineering, Mathematics, or a related field.
- Experience programming with at least one software programming language.
- Preferred: experience with CUDA kernels or ML/low-level kernels and with machine learning and large language model fundamentals, including model architecture, training and inference lifecycles, and execution optimization.
Benefits
- Comprehensive medical, dental, vision, prescription, life and AD&D insurance, with supplemental life plan options.
- Employee Assistance Program, mental health support, medical advice line, flexible spending accounts, and adoption and surrogacy reimbursement.
- 401(k) matching, paid time off, and parental leave.
- Sign-on payments and restricted stock units are included in the Amazon package.
- Work location: Bellevue, Washington, USA.
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.