Description

You will design and build scalable infrastructure and data pipelines to support Generative AI architectures, including RAG, summarization, and agents.

This role is on-site.

Responsibilities

• Design fault-tolerant infrastructure for RAG, summarization, and agent-based architectures.
• Build and maintain IaC using Terraform or CloudFormation, and CI/CD pipelines via Jenkins, CodePipeline, uDeploy, and GitHub Actions.
• Develop data ingestion pipelines for fine-tuning LLM models and build HITL feedback systems for supervised fine-tuning.
• Create architecture-as-code templates implementing reference architecture topologies.
• Collaborate with cloud, security, and data science teams to develop a self-service internal developer Generative AI platform.

Required Skills

• 8+ 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.
• 4+ years of experience working with AWS cloud services.
• Extensive programming experience with Python and Java.
• Strong proficiency in embeddings, ANN/KNN, vector stores, database optimization, and performance tuning.
• Experience with LLM orchestration frameworks such as Langchain or LlamaIndex.
• Foundational understanding of Natural Language Processing and Deep Learning.
• Experience with CI/CD pipelines, automated testing, automated deployments, and Agile methodologies.
• Knowledge of distributed NoSQL database systems.

Preferred Skills

• Experience with AWS OpenSearch, SageMaker, API Gateways, and ECS/Docker.
• Proficiency in RAG pipeline customization, including model fine-tuning, retrieval re-ranking, and HNSW.

Key Skills

Education

Any Graduate