Software Development Engineer II, SageMaker AI Inference

Market insights

Stack

Free, after you sign in.

Apply

Upload your CV — employers and recruiters from different countries looking for your profile can contact you directly.

Description

Demand for large language model (LLM) inference is growing fast, and the engineers who make it faster and more efficient are shaping the future of AI at Amazon. We are looking for a Software Development Engineer to focus on inference performance optimization, kernel tuning, and LLM serving efficiency. You will work across the full software development lifecycle to design, build, and measure systems that reduce latency and improve throughput for production inference workloads. This is a hands-on engineering role where your work directly translates into better performance for internal teams and, ultimately, for Amazon's customers. If you are an engineer who enjoys profiling bottlenecks, writing high-performance code, and finding elegant solutions to hard systems problems, we want to talk to you.<br/><br/>Key job responsibilities<br/>- Design and implement kernel-level optimizations and inference pipeline improvements that reduce latency and increase throughput for LLM serving workloads.<br/>- Profile, benchmark, and tune model inference performance across hardware and software stacks, identifying bottlenecks and delivering measurable gains.<br/>- Write well-organized, maintainable code and participate actively in code reviews, providing constructive feedback to peers and mentoring newer engineers on the team.<br/>- Collaborate with applied scientists, ML engineers, and infrastructure teams to translate model requirements into production-ready inference solutions.<br/>- Evaluate

Full description, company and the link to apply — after you sign in. Sign in

Employer contacts (email/phone/telegram) are hidden from the public preview. Send your CV so employers can reach you directly.