LLM-Driven Backend Engineer for AI Assistants

Amazon; Boulder (CO); On-site; USD 144,000 - 194,000; Full time

Job summary

Amazon.com Services LLC’s AMC Assistant team is building an AI-powered conversational agent that lets advertisers interact with AMC through natural language, replacing SQL queries and complex UIs. You’ll work at the intersection of LLMs, distributed systems, and petabyte-scale advertising data to ship a high-visibility product at the forefront of generative AI in advertising.

As an SDE II, you will design backend services, own end-to-end delivery, build scalable data pipelines, and collaborate

Qualifications

• 3+ years of professional software development experience.
• 2+ years of design or architecture experience of large-scale systems.
• 1+ years of software development engineer experience.
• 1+ years of experience with large-scale distributed software applications.
• 1+ years of Object Oriented Design experience.
• Experience programming with at least one programming language.

Responsibilities

• Design, develop, and maintain backend services powering the AMC conversational assistant.
• Build and optimize LLM orchestration pipelines including prompt engineering and agent workflows.
• Develop APIs and integrations with AMC's query engine and reporting services.
• Collaborate with applied scientists to integrate ML models.
• Contribute to the evaluation framework and agent accuracy.

Skills

Software development

System design

Distributed systems

C#/C++/Java

OO Design

Programming languages

Education

Bachelor's degree in CS or equivalent

Tools

AWS services

Job description

Amazon.com Services LLC’s AMC Assistant team is building an AI-powered conversational agent that lets advertisers interact with AMC through natural language, replacing SQL queries and complex UIs. You’ll work at the intersection of LLMs, distributed systems, and petabyte-scale advertising data to ship a high-visibility product at the forefront of generative AI in advertising.

As an SDE II, you will design backend services, own end-to-end delivery, build scalable data pipelines, and collaborate