Description

You will design and implement scalable infrastructure to move Generative AI research into production. You own the fault-tolerant architecture for RAG, summarization, and agents.

Responsibilities

• Design and build fault-tolerant infrastructure for Generative AI reference architectures, including RAG, summarization, and agents.
• Build and maintain IaC, CI/CD scripts, and deployment pipelines using Terraform, CloudFormation, Jenkins, CodePipeline, uDeploy, and GitHub Actions.
• Develop a self-service internal developer Generative AI platform in collaboration with data science teams.
• Design and build data ingestion pipelines for LLM fine-tuning and create feedback systems using HITL for supervised fine-tuning.
• Create Architecture as Code templates implementing reference architecture application topology.

Required Skills

• 12+ years of experience building and shipping software or platform infrastructure solutions for enterprises.
• 8+ years of experience designing and building data-intensive solutions using distributed computing.
• 6+ years of experience with AWS cloud.
• Extensive programming experience with Python and Java.
• Proficiency with AWS stack including Lambda, Step Functions, API Gateway, and ECS/Docker.
• Experience with CI/CD pipelines, automated testing, automated deployments, and Agile methodologies.
• Strong understanding of LLM orchestration frameworks like Langchain or LlamaIndex.
• Foundational understanding of Natural Language Processing and Deep Learning.
• Knowledge of distributed NoSQL database systems.
• Bachelor's degree in Computer Science, Computer Engineering, or a technical field.

Preferred Skills

• Experience with AWS OpenSearch, SageMaker, data engineering, ETL, and conversational UX.
• Knowledge of HPCs, vector embedding, hybrid/semantic search, and HNSW.
• Proficiency in RAG pipeline customization, including retrieval re-ranking and model fine-tuning.

Key Skills

Education

Any graduate