Role: Lead GenAI / AI-ML SME – Network Anomaly Agentic Program

Job ID: DOX1JP00011511

Employment Type: Full Time

Work Mode: Onsite – Client Interview and Worksite

Role Overview

We are looking for a Lead GenAI / AI-ML Subject Matter Expert (SME) to lead the design and development of an Agentic AI solution focused on network anomaly detection, investigation, and operational intelligence. The role requires hands-on expertise in LLM-powered agents, Retrieval-Augmented Generation (RAG), prompt engineering, and AI solution architecture. The ideal candidate will combine strong Python development skills with technical leadership and consulting abilities to translate network operations requirements into scalable AI solutions. Production monitoring experience is an added advantage, while the primary focus remains on AI architecture, agent development, RAG implementation, and network anomaly use cases.

Job Duties and Responsibilities

• Serve as the AI/ML SME for a network anomaly Agentic AI program, providing guidance on solution design, technical direction, and implementation approaches.
• 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, technical documentation, incident history, knowledge bases, and operational procedures.
• Lead prompt engineering, tool calling, agent routing, structured outputs, and evaluation methods to ensure reliable AI-assisted network operations.
• Collaborate with architects, engineers, data teams, product owners, and client stakeholders to translate business and network operations requirements into actionable AI capabilities.
• Support code reviews, architecture discussions, sprint delivery, technical documentation, and knowledge sharing across the GenAI engineering team.

Required Qualifications and Skills

• Strong Python software engineering experience with hands-on delivery of GenAI, AI/ML, or LLM-based applications.
• Experience with LangChain, LangGraph, or equivalent Agentic AI 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 work as a technical SME with strong communication, consulting, solution design, and stakeholder management skills.
• Working knowledge of cloud AI services, APIs, databases, observability, testing, and production deployment practices.
• Experience with network operations, anomaly detection, incident analysis, telecommunications, or enterprise operations is preferred.

Preferred Certifications

• AWS, Azure, or Google Cloud AI/ML certification.
• Relevant certifications or training in artificial intelligence, machine learning, data engineering, cloud architecture, or software engineering.
• Network, telecom, or operations-focused certifications.

Technical Skills / Tech Stack

Core AI / GenAI

• Python
• Large Language Models (LLMs)
• LangChain and LangGraph
• Retrieval-Augmented Generation (RAG)
• Prompt engineering
• Tool-calling agents and multi-agent workflows

Network Anomaly Program

• Network anomaly detection
• Incident triage
• Root-cause investigation
• Operational intelligence

Data and Search Technologies

• Vector search and embeddings
• Hybrid retrieval and re-ranking
• OpenSearch
• Pinecone
• pgvector
• PostgreSQL

Secondary Skills

• Cloud AI services
• Observability and monitoring
• Testing and quality assurance
• Production deployment practices
• API and database integration

Key Skills at a Glance

• Programming: Python
• AI/ML: GenAI, LLMs, Agentic AI
• AI Frameworks: LangChain, LangGraph
• RAG & Search: Embeddings, vector search, hybrid retrieval, re-ranking
• AI Engineering: Prompt engineering, tool calling, agent orchestration
• Network Operations: Anomaly detection, incident triage, root-cause analysis
• Data Technologies: OpenSearch, Pinecone, pgvector, PostgreSQL
• Professional Skills: Technical leadership, consulting, solution design, stakeholder communication