About the role

The Agentic AI Specialist is the technical authority and “master” across AI technologies within the AI Factory. You will enable and guide developers (working under the Engineering Manager) to Plan, build, and operate enterprise-grade AI agents using Azure OpenAI, Copilot Studio, and ServiceNow (including integrations across enterprise knowledge, workflows, and tooling).
You will define reference architectures, engineering standards, and guardrails; lead complex technical decisions; and ensure delivery is measurable, predictable, secure, reliable, and cost-effective. This role combines hands-on engineering (coding, debugging, reviewing, automation) with technical leadership (roadmaps, tooling, quality systems, mentorship, innovation).

What you’ll be doing

1) Engineering Strategy, Predictability & Measurability
•    Deliver the AI Factory engineering strategy so teams can build high-quality agentic solutions with predictable outcomes (capacity planning, delivery metrics, quality gates, cost-to-serve tracking, platform SLAs).
2) Technical Decisions & Architecture Across Platforms
•    Make complex technical decisions spanning Azure OpenAI model choices, orchestration patterns, Copilot Studio plan, ServiceNow integration patterns, and enterprise architecture.
3) Solve Strategic/Complex Problems with Leading-edge Solutions
•    Resolve complex agentic issues: prompt injection, tool misuse, grounding failures, hallucinations, latency spikes, knowledge freshness, agent memory pitfalls, and secure tool execution at scale.
4) Execute & Contribute to the Technical Roadmap
•    Define and execute a roadmap for:
o    Azure OpenAI capability adoption (models, embeddings, content filtering, caching)
o    Copilot Studio extensibility (connectors, actions, plugins)
o    ServiceNow AI experiences (Virtual Agent/Now Assist patterns, strategy triggers)
o    Shared runtime components (tool registry, policy engine, evaluation services)
5) Engineering & Operational Excellence (Metrics + Improvement Loops)
•    Establish excellence practices: definition-of-done for AI, release criteria, evaluation regression suites, security reviews, performance baselines, and runbooks.
6) Foster Innovation with High Reliability
•    Create a culture of rapid experimentation with controls: safe sandboxes, feature flags, A/B tests, prompt/version governance, and production readiness checklists.
7) Hands-on Coding, Testing & Reviews
•    Write, test, and review code across agent services, middleware, connectors, and orchestration logic; refactor prompt flows and agent policies as required.
8) Resolve Escalations (Deep Technical Troubleshooting)
•    Debug and troubleshoot across:
o    Agent orchestration services
o    Prompt strategy + evaluation failures
o    ServiceNow integrations / APIs
o    Copilot Studio action chains
o    Identity/access issues (Entra ID)
o    Observability traces and incidents
9) Drive Technical Vision & Innovation
•    Contribute to the broader technical direction: new patterns for agent planning/routing, safe tool calling, RAG design, memory strategies, and cross-platform integration.
10) Tooling & Automation for Developer Productivity
•    Implement and maintain CI/CD and automation:
o    Prompt + flow versioning
o    Automated eval pipelines
o    Quality gates (groundedness, relevance, toxicity checks)
o    Automated release validation
o    Developer templates and scaffolding
11) Architectures & Standards for Enterprise Scale
•    Define enterprise standards for:
o    Agent runtime design
o    RAG architecture (indexing, retrieval, citations)
o    Secure tool execution patterns
o    Data access boundaries
o    Tenant-level governance + audit logging
o    Multi-environment promotion (dev/test/prod)
12) Build New Software + Data-driven Improvements (Reduce Tech Debt)
•    Research, design, and build new components, and perform deep analysis of agent telemetry to reduce tech debt and improve reliability, performance, and developer experience.
13) Mentorship & Technical Coaching
•    Mentor engineers and squads via design reviews, code reviews, pairing sessions, office hours, and playbooks.
14) Knowledge Leadership & Emerging Trends
•    Continuously research and share best practices in agentic AI, LLMOps, Responsible AI, evaluation techniques, and platform feature evolution.

Essential Skills / Experience

Technical (Must-have)
•    Strong experience building LLM-powered solutions (RAG, tool calling, prompt engineering, evaluation-driven development).
•    Strong engineering background in Python and/or TypeScript/C# with production-grade quality.
•    Experience with Azure components relevant to AI workloads (APIs, security, monitoring, pipelines).
•    Ability to plan scalable enterprise architectures and integration patterns.
Platform (Must-have for this role)
•    Hands-on experience with Azure OpenAI (model usage patterns, embeddings, filtering/safety, cost optimisation).
•    Experience building copilots/assistants using Copilot Studio (connectors/actions/flows).
•    Experience integrating with ServiceNow (workflows, APIs, automation patterns; AI/Virtual Agent exposure is a plus).
Engineering Excellence
•    CI/CD, automated testing, code review discipline, documentation playbooks.
•    Observability and production support mindset (SLOs, incident response, postmortems).
Security & Governance Mindset
•    Understanding of identity/access controls, secure integration, and AI risk controls.
•    Ability to implement guardrails that prevent unsafe or non-compliant agent behaviour.

Desirable Skills / Experience

•    LLMOps/AgentOps tooling experience (evaluation pipelines, prompt versioning, tracing frameworks).
•    Knowledge of Microsoft governance/security ecosystem (e.g., Entra ID, Purview concepts, SOC/monitoring practices).
•    Experience implementing knowledge ingestion pipelines and vector stores.
•    Experience with ServiceNow CoE operating models and enterprise platform governance.