Software Development Engineer - Multi-Modal RAG Pipelines

Amazon Inc.; Seattle (WA); On-site; USD 144,000 - 194,000; Full time

Job summary

Amazon Inc. is seeking a Software Development Engineer to join the AWS Quick RAG team, working on retrieval-augmented generation tech powering Quick Suite's document processing and search capabilities.

You will design and build scalable ingestion pipelines for multi-modal content (PDF, audio, video, tables) using computer vision and ML, optimizing performance for millions of documents with AWS Bedrock, ECS, and DynamoDB.

Qualifications

• 3+ years of non-internship professional software development experience.
• 2+ years of non-internship design or architecture experience of new and existing systems.
• 1+ years of software development engineer or related occupational experience.
• 1+ years of designing and developing large-scale, multi-tiered, multi-threaded, distributed software applications, tools, systems, and services using: C#, C++, Java, or Perl experience.
• 1+ years of Object Oriented Design experience.

Responsibilities

• Design, develop, test, and deploy distributed machine learning systems and large-scale solutions.
• Collaborate to influence team strategy and road map; drive system architecture and best practices.
• Mentor junior engineers through code reviews and technical discussions.

Skills

3+ yrs software dev

2+ yrs design/architecture

1+ yrs SDE experience

Large-scale distributed systems

OO design

Programming language experience

Education

Bachelor's degree in Computer Science/Engineering/Math

Bachelor's degree in CS or equivalent

Job description

Amazon Inc. is seeking a Software Development Engineer to join the AWS Quick RAG team, working on retrieval-augmented generation tech powering Quick Suite's document processing and search capabilities.

You will design and build scalable ingestion pipelines for multi-modal content (PDF, audio, video, tables) using computer vision and ML, optimizing performance for millions of documents with AWS Bedrock, ECS, and DynamoDB.