AI/ML SME
Kanusha SharmaRemoteSENIORPosted 12d ago
PythonGenAIAIMLLLMLangChainLangGraphprompt engineeringtool callingagent routingstructured outputsRAGvector searchhybrid retrievalre-rankingcloud AI servicesAPIsdatabasesobservabilitytestingproduction deploymentAWSAzureGoogle Cloudnetwork operationsanomaly detectionincident analysistelecommunications
About the Role
We are seeking an AI/ML SME to join a network anomaly agentic AI program. This role requires hands-on experience with AI/ML technologies and the ability to translate network operations requirements into scalable agentic AI capabilities.
Key Responsibilities
• Serve as the AI/ML SME for a network anomaly agentic AI program, advising on solution design, technical direction, and implementation approach.
• Design and develop LLM-powered agents and multi-agent workflows for network anomaly detection, triage, root-cause investigation, and operational insight generation.
• Build RAG capabilities using network data, documentation, incident history, knowledge bases, and operational procedures.
• Lead prompt engineering, tool-calling, agent routing, structured outputs, and evaluation patterns for reliable AI-assisted network operations.
• Partner with architects, engineers, data teams, product owners, and client stakeholders to convert business and network operations needs into actionable AI capabilities.
• Support code reviews, architecture discussions, sprint delivery, documentation, and knowledge sharing across the GenAI engineering team.
Requirements
• Strong Python software engineering experience with hands-on GenAI, AIML, or LLM-based application delivery.
• Experience with LangChain, LangGraph, or equivalent agenticAI frameworks.
• Strong understanding of LLM APIs, tool calling, prompt engineering, structured outputs, streaming, and agent orchestration patterns.
• Experience designing RAG solutions using embeddings, vector search, hybrid retrieval, re-ranking, and answer generation.
• Ability to operate as a technical SME with strong communication, consulting, solution design, and stakeholder-facing skills.
• Experience with network operations, anomaly detection, incident analysis, telecommunications, or enterprise operations use cases preferred.
• Working knowledge of cloud AI services, APIs, databases, observability, testing, and production deployment practices.