Build and deploy RAG (Retrieval-Augmented Generation) pipelines for enterprise use cases and develop agentic AI solutions using LangChain and AWS Bedrock/Foundational Models
Job Summary
Build and deploy RAG (Retrieval-Augmented Generation) pipelines for enterprise use cases and develop agentic AI solutions using LangChain and AWS Bedrock/Foundational Models.
Train, evaluate, and deploy machine learning models on AWS SageMaker, implementing MLOps best practices including model versioning, CI/CD, monitoring, and performance tracking.
Mentor junior AI/ML resources and collaborate with cross-functional teams to align AI solutions with business goals, communicating AI/ML strategies and insights to both technical and non-technical stakeholders.
Matching Summary
Build and deploy RAG (Retrieval-Augmented Generation) pipelines for enterprise use cases and develop agentic AI solutions using LangChain and AWS Bedrock/Foundational Models.
Skills & Requirements
Must-have
Generative AI
LLM Development
RAG pipelines
LangChain
AWS Bedrock
vector databases
AWS SageMaker
MLOps best practices
CI/CD
model versioning
Nice-to-have
collaboration
wellbeing
inclusive environment
technical and non-technical audiences
emerging frameworks
Key Requirements
Experience with Generative AI and LLM development
Experience with MLOps best practices
Experience integrating AI features into core applications