Software Development Engineer, AI Runtime
Pune · On-site · 3+ yrs · Mid · Full-time
- alexa
- llm
- distributed systems
Build and scale AI runtime infrastructure for Alexa+ multi-agent systems and LLM orchestration pipelines at Pune office.
Apply on Amazon's site Ask for a referral Interview prep
Interview prep: questions this posting points to
- Walk me through how you'd design a serverless, event-driven pipeline on AWS that takes a GenAI/LLM model's output and turns it into personalized marketing content delivered across multiple channels like social media and YouTube at EU scale. What AWS services would sit where, and how do you handle backpressure if the LLM inference is slow?
- It's the middle of a major marketing campaign push for Prime, and your GenAI-powered personalization service starts timing out intermittently, causing some customers to see generic fallback content instead of personalized offers. Walk me through how you'd triage this live.
- Tell me about a time you had to balance shipping a new feature with keeping a system reliable and performant — how did you make that trade-off decision?
Read the full job description
We are looking for a passionate and experienced Software Development Engineer to help us build and scale the next generation of AI runtime infrastructure for Alexa+. You will design and implement Tier-1 distributed systems that orchestrate expert agent executions, manage LLM inference pipelines, and ensure reliable, low-latency delivery across Alexa-enabled devices globally. This is a high-impact role where your work directly shapes how millions of customers experience Alexa+ every day. Key job responsibilities - Design, build, and operate large-scale distributed services that power Alexa+ Expert executions - Develop and optimize LLM orchestration pipelines — including model serving, prompt routing, and inference optimization - Build multi-agent coordination systems that route requests to the right expert agents with minimal latency - Own the operational excellence of Tier-1 services, ensuring 99.99%+ availability at scale - Collaborate with applied scientists and ML engineers to integrate new AI capabilities into production - Drive architectural decisions that balance performance, reliability, and cost efficiency - Mentor teammates and raise the engineering bar through code reviews, design reviews, and technical leadership
About the team
The AI Runtime team is the backbone of Alexa+. We own the infrastructure that powers Expert executions — the multi-agent systems that bring Alexa+'s intelligent capabilities to life for hundreds of millions of customers worldwide. Our services orchestrate LLM inference, coordinate expert agents, and deliver responses at massive scale with low latency. When a customer interacts with Alexa+ and it feels magical, our platform made it happen.
Basic qualifications
- 3+ years of non-internship professional software development experience - 2+ years of non-internship design or architecture (design patterns, reliability and scaling) of new and existing systems 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 qualifications
- 3+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience - Bachelor's degree in computer science or equivalent - System design with AI components and able to evaluate latency, cost, reliability, and accuracy. 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.
Members get roles like this as soon as we find them on the company's careers page, and paid plans email the ones that match their resume.
Get new roles first — free