Description

You will design and build scalable, secure GenAI and LLM-powered solutions on AWS. You own the full lifecycle from RAG pipeline implementation to API deployment, monitoring, and cost optimization.

This role is on-site.

Responsibilities

• Design and implement RAG pipelines, including data ingestion, embeddings, vector search, and prompt engineering.
• Develop and deploy GenAI APIs and services using AWS Bedrock and SageMaker with CI/CD and IaC.
• Implement security, compliance, and Responsible AI guardrails, including PII handling, IAM, and governance controls.
• Optimize system performance, monitoring, and costs for scalable architectures.
• Collaborate with stakeholders to translate business requirements into technical solutions.

Required Skills

• 10+ years of software engineering experience.
• Strong proficiency in Python and PySpark.
• Hands-on experience with AWS services: Amazon Bedrock, SageMaker, and IAM.
• Experience building RAG systems, vector search, and hallucination control.
• Proficiency in CI/CD pipelines and Infrastructure as Code (IaC).
• Knowledge of Kubernetes and containerization.
• Understanding of AI/GenAI frameworks and Responsible AI principles.

Preferred Skills

• Experience with large-scale data processing and distributed systems.
• Strong communication skills for cross-functional stakeholder management.

Key Skills

Education

Any Gradute