Description

You will design and implement ML models and LLM integrations for IT operations analytics, AIOps, and connector health monitoring.

This role is on-site.

Responsibilities

• Build supervised and unsupervised learning pipelines for predictive failure analysis and anomaly detection.
• Integrate LLM APIs (AWS Bedrock, OpenAI, Anthropic) into orchestration workflows and build RAG pipelines for documentation search and incident summarization.
• Develop agentic AI pipelines using LangChain or CrewAI for autonomous incident triage and connector lifecycle management.
• Deploy and manage LLM inference endpoints on AWS Lambda, ECS, or SageMaker with secure access controls.
• Maintain MLOps best practices including model versioning, drift monitoring, feature stores, and automated retraining.

Required Skills

• 5+ years of hands-on experience in ML engineering, AI application development, or data science.
• Strong proficiency in Python and Java for building scalable AI services and REST APIs.
• Experience with AWS AI/ML services including SageMaker, Bedrock, Comprehend, and OpenSearch.
• Proficiency in building CI/CD pipelines using Jenkins, GitHub Actions, or GitLab CI.
• Experience with containerization and orchestration using Docker and Kubernetes.
• Knowledge of SQL for data querying and management.
• Background in Data Science with experience in time-series forecasting and NLP techniques.

Preferred Skills

• Experience with LLM frameworks like LangChain, CrewAI, or AutoGen.
• Familiarity with AWS security best practices including IAM, KMS, and VPC.

Key Skills

Education

Bachelor's degree