Software Development Manager - NKI, AWS Neuron, Annapurna Labs

Overview

Software Development Manager with strong leadership and mentoring skills to join the NKI development team. As an SDM III, you will lead a team of experienced compiler engineers developing compiler optimization algorithms and deploying, at scale, a new compiler targeting AWS custom hardware. You will draw on knowledge of resource management, scheduling, code generation, optimization, and instruction architectures across CPU, NPU, GPU, and novel forms of compute.

You will leverage your technical communication skills to partner with AWS ML services teams and pre-silicon design, and to bring new products and features to market. You will help the team build software that boosts the entire deep learning community.

Explore the product and team context: AWS Neuron SDK, NKI compiler, and Trainium accelerators enable high-performance ML in the cloud. The Annapurna Labs team builds silicon and software for AWS customers and collaborates across silicon engineering, hardware design, software, and operations.

• Lead, grow, and mentor a team of compiler engineers, including hiring, career development, and team health
• Own execution and delivery of NKI compiler features across release cycles, balancing scope, quality, and timelines
• Set technical direction and roadmaps for the NKI compiler in partnership with senior engineers
• Partner across teams (frameworks, kernel development, runtime, hardware/pre-silicon design, product management) to bring new features to market
• Drive resolution of complex, high-priority technical issues, staying close to code and hardware to guide the team
• Represent the team s work and priorities to senior leadership and cross-organizational stakeholders
• Anchor decisions in customer impact, ensuring the team builds what unblocks real ML workloads on Trainium

No two days are the same; most days blend people leadership, technical depth, and cross-team collaboration. You may 1:1 with engineers, participate in release syncs, and coordinate with partner teams on feature dependencies. In the afternoon, you work on the roadmap, review designs, provide feedback, and analyze profiling results to improve performance. You finish by clearing paths for the team, resolving escalations, and enabling fast progress tomorrow.

The central question is: what does this unblock for our customers?

Inclusive Team Culture:
We embrace differences and strive for inclusion. We value learning, diverse perspectives, and earning trust as part of Amazon s Leadership Principles.

Work/Life Balance:
We promote flexible working hours to support a healthy balance between personal and professional life.

Mentorship & Career Growth:
We support knowledge sharing and mentorship, with opportunities for project assignments that develop engineers into more capable practitioners.

• 5+ years of engineering team management experience
• 9+ years of working directly within engineering teams
• 4+ years of designing or architecting new or existing systems (design patterns, reliability, scaling)
• Experience partnering with product or program management teams
• Understanding of compilers (resource management, instruction scheduling, code generation, compute graph optimization)
• Strong software design fundamentals and excellent system-level coding skills

• M.S. or Ph.D. in Computer Science or related technical field

Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status.

Location:

Cupertino, CA. Eligible for relocation as needed.

The base salary range for this position is listed below. Your Amazon package includes sign-on payments and RSUs. Final compensation is determined based on experience, qualifications, and location. Benefits include health insurance, 401(k) matching, paid time off, parental leave, and more. Learn more about our benefits at (Use the "Apply for this Job" box below)..

For context, see product pages and docs:

• -

Posted dates and internal notes removed to focus on the role-specific content.