Accepting Applications
Full-time
On-site
Posted 1 hour, 18 minutes ago
0 views
0 applications
Job Description
**KEY RESPONSIBILITIES**
* Engineer and operationalize Generative AI workflows within ServiceNow Now Assist and AI Control Tower, leveraging proprietary LLM models and Azure OpenAI endpoints.
* Build and govern RAG (Retrieval\-Augmented Generation) pipelines that ground ServiceNow virtual agents in internal knowledge bases, SOPs, and technical documentation corpora.
* Manage the full LLMOps lifecycle — prompt versioning, model drift monitoring, hallucination guardrails, and cost optimization — within the ServiceNow AI Control Tower observability layer.
* Develop custom Now Assist skill extensions using GenAI Studio, integrating with internal APIs and ERP/EAM systems.
* Establish AI quality gates within ServiceNow AI Control Tower to monitor LLM response accuracy, latency SLAs, and safety guardrails across all deployed AI agents.
* Design and implement vector embedding pipelines for 40\+ years of petro\-technical documentation, enabling semantic search within ServiceNow.
* Produce MLOps dashboards within AI Control Tower tracking token consumption, model performance KPIs, and ROI metrics across all AI initiatives.
**MANDATORY QUALIFICATIONS**
* 8\+ years of software engineering with minimum 4 years on ServiceNow platform and 2\+ years in LLMOps or MLOps.
* Certified ServiceNow Developer (CSD) with AI/Now Assist specialization or equivalent demonstrable expertise.
* Hands\-on production experience building RAG pipelines using LangChain, LlamaIndex, or equivalent frameworks.
* Proficiency with vector databases (Pinecone, Weaviate, Chroma, or Azure AI Search).
* Experience managing LLM deployments on Azure OpenAI Service or AWS Bedrock within enterprise IT environments.
* Strong Python, REST API, and ServiceNow Scripting (GlideScript/Rhino) expertise.
* Bachelor's or Master's degree in Computer Science, AI Engineering, or Data Science.
Login to Apply
Don't have an account? Register