Sr. Software Dev Engineer, Alexa LLM Inference, Capacity, & Efficiency
Posted Oct 28, 2026·Open for 0 days (and counting)
Are you a recruiter or hiring manager?
Generate a McCoy IQ challenge in 30 seconds.
See how candidates think and approach the work this role demands, before the phone screen. We'll build a video challenge from this posting, and you can edit or share it before it goes live.
Key details
Function
Engineering
Seniority
Senior
Workplace
On-site
Location
Bengaluru, IND
Specialty
LLM Inference Infrastructure
Tech stack
JavaC++C#
Why this role is notable
Amazon is standing up a dedicated LLM inference, capacity, and efficiency team in India to run Alexa's large-scale AI serving infrastructure, signaling that the cost and reliability of serving LLMs at massive scale is now a core, separately staffed priority rather than a side task of model development.
Archetype: Engineering
Job Description
Are you passionate about building and operating the world's largest real-time LLM inference systems? Are you a technical leader who thrives in high-ambiguity environments and wants to drive architectural decisions that impact millions of Alexa customers daily? If so, the Alexa LLM Inference, Capacity, & Efficiency (ALICE) team is looking for a Senior Software Development Engineer to join our new India team and own critical components of Alexa's LLM inference infrastructure.
Alexa is shaping the future of AI voice-based personal assistants. At ALICE, we are passionate about infrastructure efficiency, cost optimization, and capacity management to enable amazing customer experiences at scale. You will be a founding technical leader of our India presence, setting the bar for engineering excellence and driving high-impact work on one of Amazon's most critical AI services.
Key job responsibilities
- Serve as a technical leader for the ALICE India team, driving architecture decisions for the AlexaLLMInferenceService (LLMI) and related ALICE portfolio services
- Design and implement scalable, high-availability systems for LLM inference serving, including multi-node distributed inference and multi-tenancy capabilities
- Lead technical design reviews, set coding standards, and mentor junior SDEs on the team
- Make technical trade-offs between short-term team needs and long-term business needs, with a focus on performance, cost, and reliability
- Collaborate with ALICE teams in Seattle and partner teams across Alexa and AGI on cross-cutting infrastructure programs
- Drive operational excellence for Tier-1 production services, including on-call ownership, incident response, and continuous improvement
- Influence the broader ALICE software architecture and contribute to org-wide technical strategy
A day in the life
As a Senior SDE, you will be part of the technical leadership for the India team, owning architecture decisions for LLMI components and contributing to ALICE's broader portfolio of infrastructure optimization products. Basic Qualifications - 6+ years of non-internship professional software development experience
- 5+ years of programming using a modern programming language such as Java, C++, or C#, including object-oriented design experience
- 5+ years of leading design or architecture (design patterns, reliability and scaling) of new and existing systems experience
- Experience contributing to the architecture and design (architecture, design patterns, reliability and scaling) of new and current systems
- Experience building complex software systems that have been successfully delivered to customers Preferred Qualifications - 5+ 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
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.
Alexa is shaping the future of AI voice-based personal assistants. At ALICE, we are passionate about infrastructure efficiency, cost optimization, and capacity management to enable amazing customer experiences at scale. You will be a founding technical leader of our India presence, setting the bar for engineering excellence and driving high-impact work on one of Amazon's most critical AI services.
Key job responsibilities
- Serve as a technical leader for the ALICE India team, driving architecture decisions for the AlexaLLMInferenceService (LLMI) and related ALICE portfolio services
- Design and implement scalable, high-availability systems for LLM inference serving, including multi-node distributed inference and multi-tenancy capabilities
- Lead technical design reviews, set coding standards, and mentor junior SDEs on the team
- Make technical trade-offs between short-term team needs and long-term business needs, with a focus on performance, cost, and reliability
- Collaborate with ALICE teams in Seattle and partner teams across Alexa and AGI on cross-cutting infrastructure programs
- Drive operational excellence for Tier-1 production services, including on-call ownership, incident response, and continuous improvement
- Influence the broader ALICE software architecture and contribute to org-wide technical strategy
A day in the life
As a Senior SDE, you will be part of the technical leadership for the India team, owning architecture decisions for LLMI components and contributing to ALICE's broader portfolio of infrastructure optimization products. Basic Qualifications - 6+ years of non-internship professional software development experience
- 5+ years of programming using a modern programming language such as Java, C++, or C#, including object-oriented design experience
- 5+ years of leading design or architecture (design patterns, reliability and scaling) of new and existing systems experience
- Experience contributing to the architecture and design (architecture, design patterns, reliability and scaling) of new and current systems
- Experience building complex software systems that have been successfully delivered to customers Preferred Qualifications - 5+ 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
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.
Interested in working for companies like this one?
Answer a McCoy challenge. Companies hiring in engineering see your response and reach out when they want to talk.
About 15 minutes to prepare and 5 minutes to record. Unlimited retakes and a teleprompter help you answer. No AI training, and you can delete your response anytime.
This isn't an application to Amazon.
Audit details(provenance, verification trail, raw fields)
Core fields
Posting ID
amazon:10586506Title
Sr. Software Dev Engineer, Alexa LLM Inference, Capacity, & Efficiency
Function
Engineering
Location
Bengaluru, Karnataka, IND
Workplace mode
unspecified
Posted at
2026-10-28 00:00:00Z
Compensation
undisclosed
Provenance
First seen (our tracker)
2026-10-28 07:27:47Z
Last seen
2026-10-28 07:27:47Z
Last updated
2026-10-28 07:54:15Z
Removed at
still open
Days open
Open for 0 days (and counting)
ATS adapter
amazon
ATS slug
amazonVerification trail
This posting hasn't been probed by our closure verifier yet. Stream C runs on a rolling schedule against postings approaching the close-decision threshold.
LLM enrichment
Enriched at 2026-10-28 07:54:15Z. Enrichment runs once per posting, never re-runs.
Seniority
ic_l3
Role archetype
engineering
Specialty
llm_inference_infrastructure
Workplace mode
unknown
City (normalized)
Bengaluru
Country (normalized)
India
Comp range
—
Tech stack
javac++c#
Notable role?
yes
See how we measure for definitions, or our corrections log for known issues. Found something wrong? Flag a correction.