JobgetherRemote · Canada
2h ago
AmazonPosted 1mo ago
L4
Software Development Student , Machine Learning Israel (MLIL) — Integration Validation
Software Development Student , Machine Learning Israel (MLIL) — Integration Validation at Amazon scores 87 out of 100 on AI centrality, which makes it a Level 4 role on this board.
IL, Tel Avivpart-time
AI in this role
vllm
Student Software Development Engineer
Annapurna Labs designs silicon and software that accelerates innovation. Our custom chips, accelerators, and software stacks enable us to take on technical challenges that have never been seen before, and deliver results that help our customers change the world.
The Integration team is looking for a Student Software Development Engineer to join us in building and validating systems software for our next-generation ML accelerator servers. In this role you will contribute to CI/CD pipelines, test automation, and system-level validation for our ML inference accelerator platform — working across firmware interfaces, data-plane components, and ML serving stacks (vLLM, NKI, NIXL).
This is a greenfield environment with rapidly growing scope: new silicon, new software stacks, and new fleet-scale challenges. You'll gain hands-on experience with production-grade infrastructure while working alongside senior engineers who will mentor you through real technical problems.
Key job responsibilities
Develop and maintain automated test suites
Contribute to CI/CD pipeline infrastructure — writing pipeline stages, triaging failures, and improving reliability.
Build tooling and scripts for performance benchmarking of ML inference workloads.
Help integrate vendor code drops into CI, ensuring quality gates catch regressions early.
Create dashboards and observability tooling that give the team visibility into test health and fleet readiness.
Leverage AI-assisted development tools (Kiro, LLM-based code generation) to accelerate development workflows.
A day in the life
You'll start by reviewing overnight CI results and helping triage failures — learning to distinguish between vendor regressions, firmware issues, and ML stack bugs. You might then work on extending a test framework so hardware engineers can validate a new component with minimal friction. After lunch you could be writing Python scripts that benchmark inference latency, or building a Grafana dashboard that tracks regression trends across builds. Throughout the day you'll collaborate with senior engineers across firmware, data-plane, and ML teams — and use AI-assisted tools to move faster.
Basic qualifications
- BSc student in Computer Science / Computer Engineering / Software Engineering / Electrical Engineering (with at least 3 semesters remaining before graduation).
- Please include a grade sheet/academic transcript along with your CV in a single PDF when submitting your application.
- Available for 2 to 3 work days per week.
Preferred qualifications
- Experience with Python and/or Bash scripting.
- Familiarity with Linux environments and command-line workflows.
- Exposure to CI/CD concepts (Jenkins, CDK Pipelines, GitHub Actions, or similar).
- Interest in ML infrastructure, hardware-software integration, or systems programming.
- Team player, excellent at multitasking and self-learning.
Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace accommodation or adjustment during the application and hiring process, including support for the interview or onboarding process, please visit https://amazon.jobs/content/en/how-we-hire/accommodations for more information. If the country/region you’re applying in isn’t listed, please contact your Recruiting Partner.
Prepare for this job
A free preview built only from this posting: what it asks for, what you could be asked in an interview, and how to adjust your resume.
Skills and AI tools this role asks for
vLLM
Questions you could be asked
- What's a project where you used vLLM hands-on?
- How would you decide a model or AI system is ready to ship?
- Tell me about a time a model underperformed in production. How did you find out, and what did you change?
Adapt your resume
- List these exact terms on your resume: vLLM. An applicant tracking system matches the wording, not the idea.
- Attach one line of real, concrete experience to at least one of them — a tool named with nothing behind it rarely survives a human read.
- Lead with what you built, trained or shipped — this role is judged on the AI system itself, not the tools around it.
Want your resume actually rewritten for this job?
The free preview above is everything we have today. A full resume rewrite is not live yet and has no price set. Join the waitlist and we will email you if we open it.
Similar roles
Data roles rated Level 4 at other companies.