Cybersecurity AI Platform Advisor (R5)

Job Title

Cybersecurity AI Platform Advisor (R5)

Role Overview

Cybersecurity AI Platform Advisor provides senior technical leadership and advisory guidance for AI-powered use cases across Eli Lilly's Cybersecurity platforms. This role owns the architectural vision and technical direction across the full delivery lifecycle - from identifying and scoping use cases through design, build, test, and production deployment - while partnering with engineering teams to execute against that architecture. Core responsibilities include architecting Agentic AI automation pipelines and RAG workflows that address real security challenges such as platform operations automation. The role requires close collaboration with security operations, data privacy, compliance, and platform engineering teams to ensure solutions are secure, explainable, and appropriate for a highly regulated pharmaceutical environment.

Key Responsibilities

Serve as the principal technical translator, converting complex business challenges into clear, actionable Agentic AI requirements.

Architect end-to-end agentic systems by defining solution blueprints, staging plans, agent roles, tool inventories, memory strategies, orchestration patterns, and inter-agent communication protocols.

Advise business stakeholders in refining AI adoption objectives and translating them into scalable, viable AI architectures.

Guide stakeholders through Proof of Concepts (PoCs) and development initiatives, from opportunity identification to production handover.

Establish agentic AI guardrails and approved architecture patterns that address prompt injection, unintended action loops, tool misuse, autonomy escalation, and lateral movement risks arising from agent-to-agent trust.

Define agentic AI security acceptance criteria, including sandboxing requirements, permission boundaries, HITL trigger conditions, and kill-switch mechanisms, before solutions progress to development.

Partner with cross-functional teams to identify, scope, and prioritise agentic AI use cases.

Maintain a version-controlled registry of agentic AI use cases, including design blueprints, threat models, tool manifests, and reusable agent patterns to support cross-team adoption.

Agentic AI Architecture Technical Advisory

Define reference architectures and technical standards for AI agents built on frameworks such as LangGraph, AutoGen, and CrewAI, enabling engineering teams to execute multi-step cybersecurity workflows autonomously and reliably

Establish and promote Agentic AI coding standards and best practices across engineering teams

Design and provide guidance on agent tool layers for security platforms, defining least-privilege access controls and strict input/output contracts for implementation by engineering teams

Architect RAG pipelines for agent knowledge retrieval by defining source validation, document-level injection protections, and context boundaries to prevent data exfiltration through agent outputs

Implement runtime enforcement engines that intercept, validate, and sanitise agent inputs, tool calls, and outputs against configurable security policies, blocking unsafe actions before execution

Implement and motivate teams to implement automations in different manual work done by teams today

Apply CI/CD, Infrastructure-as-Code, and version control practices to agent configurations, tool definitions, prompt templates, and orchestration logic to ensure reproducibility and auditability

Testing, Safety Validation

Design and execute agentic-specific test plans covering multi-step reasoning accuracy, tool call correctness, loop detection, boundary enforcement, and failure mode handling across diverse scenario types

Validate that human-in-the-loop checkpoints, sandboxing controls, permission gates, and emergency kill-switch mechanisms engage correctly under adversarial and edge-case conditions

Benchmark production-candidate agents against security policy compliance, action explainability, latency SLAs, and cost efficiency before sign-off for deployment

Production Deployment Lifecycle Management

Deploy agentic AI systems to enterprise cloud environments (AWS, Azure, GCP) with structured action logging, decision tracing, cost monitoring, and real-time alerting on anomalous agent behaviour

Implement agent health monitoring covering task completion rates, tool failure patterns, reasoning drift, and policy enforcement effectiveness - with automated alerts and rollback triggers

Manage the full agentic lifecycle: version-controlled agent releases, controlled rollouts, A/B evaluation of agent variants, scheduled re-validation against updated threat landscapes, and deprecation of obsolete agents

Integrate agents with upstream / downstream security platforms - SIEM, SOAR, EDR, identity, and ticketing systems - through governed API layers that enforce authentication, rate limits, and action audit trails

Provide Level 3 engineering support for agentic incidents including runaway action loops, unexpected tool invocations, and agent-induced security events - with structured post-incident reviews

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.