(Fall 2026) Annapurna Labs at AWS Internship (US) - Machine Learning Systems & Silicon Innovation

Amazon • Cupertino, CA

1d • Onsite

About The Position

At Annapurna Labs, an Amazon company, we are accelerating the AI revolution by designing custom silicon and revolutionary software systems that power the world's most advanced AI infrastructure at AWS. This includes training the largest language models and developing breakthrough ML accelerator chips, inventing the future of cloud computing. We are seeking bold innovators and builders for our Fall 2026 internship program. Interns will work on projects that directly impact millions of AWS customers worldwide, tackling real technical challenges that push the boundaries of what's possible in AI acceleration. The program offers multiple technical tracks, matching skills and interests with projects across the organization. The internship program is built on a foundation of meaningful work and genuine mentorship, fostering a diverse cohort of interns from universities nationwide. Many senior engineers at Annapurna Labs began their careers as interns, creating a culture where mentorship is integral. The experience blends hands-on technical work with opportunities to connect with fellow interns through team events, tech talks, and social activities, with many interns returning as full-time engineers.

Requirements

• Work 40 hours/week minimum and commit to 12 week internship maximum
• Currently pursuing a BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or related technical field
• Must be enrolled in a full-time degree program at time of application and returning to school after the internship
• Programming experience in C, C++, Python, or similar languages
• Experience in two or more of the following areas: Systems programming or low-level software development, Compiler design or optimization, Machine learning frameworks (PyTorch, JAX, TensorFlow), Distributed systems or parallel computing, Performance analysis and optimization, Hardware design (RTL, Verilog, FPGA development)

Nice To Haves

• Previous internship, research, or project experience in hardware/software co-design, ML systems, or computer architecture
• Contributions to open-source projects or research publications
• Completed or currently enrolled in coursework covering machine learning, parallel computing, computer architecture and/or compiler construction

Responsibilities

• Framework Optimization (PyTorch, JAX)
• Compiler Development & Optimization
• Distributed Training Systems
• Performance Engineering
• ML Infrastructure Development
• Firmware & Driver Development
• Runtime Systems
• Fleet Management & Automation
• Hardware/Software Integration
• Performance Analysis Tools
• RTL Development for ML Accelerators
• Hardware Architecture & Modeling
• Physical Design & Power Optimization
• Custom Circuit Design
• Pre/Post Silicon Validation

Benefits

• EAP
• Mental Health Support
• Medical Advice Line
• 401(k) matching

What This Job Offers

• Job Type: Full-time
• Career Level: Intern