ServiceNow Engineer – LLMOps & Gen AI

About the role

We are seeking an experienced ServiceNow Engineer to lead the design, implementation, and operationalization of Generative AI solutions within ServiceNow Now Assist and AI Control Tower. The role focuses on integrating proprietary LLM models and Azure OpenAI services to enhance virtual agents and enterprise workflows.

Key responsibilities

• Engineer and operationalize Generative AI workflows in ServiceNow Now Assist and AI Control Tower using Azure OpenAI endpoints.
• Build and govern Retrieval‑Augmented Generation (RAG) pipelines that connect virtual agents to internal knowledge bases, SOPs, and technical documentation.
• Manage the full LLMOps lifecycle, including prompt versioning, model drift monitoring, hallucination guardrails, and cost optimization.
• Develop custom Now Assist skill extensions via GenAI Studio, integrating with internal APIs and ERP/EAM systems.
• Establish AI quality gates to monitor response accuracy, latency SLAs, and safety across all deployed AI agents.
• Design vector embedding pipelines for decades of petro‑technical documentation to enable semantic search.
• Create MLOps dashboards tracking token consumption, model performance KPIs, and ROI metrics.

Required profile

• 8+ years of software engineering experience, with at least 4 years on the ServiceNow platform.
• 2+ years of hands‑on experience in LLMOps or MLOps.
• Certified ServiceNow Developer (CSD) with AI/Now Assist specialization or equivalent expertise.
• Bachelor's or Master's degree in Computer Science, AI Engineering, or Data Science.

Required skills

• ServiceNow platform development and scripting (GlideScript/Rhino).
• Python programming.
• REST API integration.
• LLMOps tools such as LangChain, LlamaIndex.
• Vector databases (Pinecone, Weaviate, Chroma, Azure AI Search).
• Azure OpenAI Service and/or AWS Bedrock deployment experience.