Description

You will design, build, and deploy agentic AI systems and LLM-based workflows in production, owning the end-to-end lifecycle from model training to inference, monitoring, and scaling on AWS.

Responsibilities

• Design and implement multi-agent architectures using LangGraph and LangChain.
• Deploy and scale AI/ML solutions on AWS, leveraging EC2, S3, Lambda, EKS, and SageMaker.
• Build and maintain end-to-end ML pipelines, including training, inference, and continuous monitoring.
• Implement Retrieval-Augmented Generation (RAG) pipelines using vector databases.
• Integrate LLMs (OpenAI, Anthropic, Bedrock) into production systems while ensuring reliability and security.

Required Skills

• 5+ years of experience in AI/ML engineering.
• Strong hands-on expertise with LangGraph and LangChain.
• Proven experience deploying agentic AI systems and LLM workflows into production.
• Advanced Python programming skills with a solid understanding of software engineering best practices.
• Deep knowledge of AWS services: EC2, S3, Lambda, EKS, SageMaker, and Bedrock.
• Experience with model deployment, monitoring, and scaling in cloud-native architectures.
• Strong understanding of LLMs, prompt engineering, and orchestration patterns.

Preferred Skills

• Experience collaborating with product and engineering teams to deliver AI features.

Key Skills

Education

Any Gradute