Description

You will design and implement machine learning models and LLM integrations for IT operations analytics, connector health monitoring, and autonomous incident triage.

This role is on-site.

Responsibilities

• Build and deploy supervised and unsupervised ML pipelines for anomaly detection and predictive failure analysis.
• Integrate LLM APIs (AWS Bedrock, OpenAI, Claude) and build RAG pipelines for documentation search and self-healing runbooks.
• Develop AI agents using LangChain, CrewAI, or AutoGen for autonomous connector lifecycle management.
• Create NLP-based log parsing and semantic classification modules to accelerate L4 support triage.
• Design agentic AI pipelines for automated defect prediction, test coverage analysis, and CI/CD integration.

Required Skills

• 8+ years of hands-on experience in ML engineering, AI application development, or data science.
• Strong proficiency with AWS AI/ML services including SageMaker, Bedrock, Comprehend, Forecast, and OpenSearch.
• Experience building RAG pipelines and managing LLM inference endpoints on AWS Lambda, ECS, or SageMaker.
• Proficiency in Python and frameworks for AI agent development (LangChain, CrewAI, AutoGen).
• Experience with vector search and semantic similarity solutions (AWS OpenSearch, Pinecone).
• Strong understanding of MLOps best practices, including model versioning, A/B testing, and drift monitoring.
• Bachelor's degree in Computer Science, Data Science, AI/ML, or Software Engineering.

Preferred Skills

• Experience integrating AI inference outputs with Java-based REST APIs.
• Familiarity with Java, Docker, Kubernetes, and CI/CD tools (Jenkins, GitHub Actions, GitLab CI).

Key Skills

Education

Bachelor's degree