The consultant will be accountable for the following four deliverables. Each deliverable must be evidenced by working artifacts (designs, code, evaluation results) and measurable outcomes.

- AI and Agentic Capability Enhancement :

i. Design, develop, and enhance AI-driven capabilities within the existing platform - leveraging LLM-based and agentic system components - while preserving the current multi-agent architecture.

ii. Extend existing agents (and, where justified, introduce new specialist agents) within the current orchestration pattern; no rearchitecture of the multi-agent foundation unless explicitly approved.

iii. Improve prompting strategies, tool-calling, retrieval (RAG), memory, and reflection/critique loops to raise reasoning quality and consistency.

iv. Harden agent behavior through evaluation harnesses, regression tests, guardrails, and observability (traceability of reasoning, safety checks, hallucination detection).

v. Document all enhancements as production-ready design specs, prompt/behavior blueprints, and runbooks.

- RCA and Recommendation Simplification :

i. Redesign the RCA narrative structure so outputs lead with the verdict, confidence, and recommended action, followed by progressively disclosed technical evidence.

ii. Introduce length, tone, and density controls at generation time (not just post-hoc summarization) so simplification does not degrade fidelity.

iii. Apply RCA methodologies (e.g., 5 Whys, Ishikawa, fault tree) inside the agentic flow so that simplified outputs remain auditable and traceable back to underlying evidence.

iv. Define and track quality metrics: diagnostic accuracy, time-to-root-cause, analyst acceptance rate, verbosity/signal ratio, and recommendation confidence calibration.

- Persona-Aware Output Adaptation :

i. Build a persona catalog covering tone, authority, decision boundaries, terminology, and escalation thresholds for each in-scope persona.

ii. Operationalize persona selection and adaptation within the agent flow (system prompts, role-conditioned generation, formatting templates) - not as a separate downstream rewrite step.

iii. Establish governance for persona changes: versioning, approval workflow, A/B testing, and rollback.

iv. Validate persona adherence through human-in-the-loop review and automated persona-conformance checks.

- Workflow and Interface Integration :

i. Integrate with existing UI surfaces and workflow tools used by frontline, supervisor, and technical support personas - without requiring users to change tools.

ii. Support real-time/low-latency delivery for live troubleshooting and batch/analytical delivery for post-ticket analysis.

iii. Integrate with enterprise data sources and tooling (telemetry, logs, knowledge bases, ticketing) through approved interfaces.

iv. Provide hypercare support post-launch: monitoring, defect triage, prompt/persona tuning, and stakeholder enablement.

2. Key Responsibilities :

- Delivery & Stakeholder Management :

i. Lead the enhancement workstream end-to-end: discovery, design, build, pilot, hardening, and hypercare.

ii. Partner with product, data, operations, risk, and compliance teams to align agent behavior and personas to business KPIs, SLAs, and risk tolerances.

iii. Define, baseline, and track success metrics (e.g., MTTR, time-to-root-cause, diagnostic accuracy, analyst acceptance, verbosity reduction, persona conformance).

iv. Present design decisions, pilot outcomes, and roadmaps to senior stakeholders in clear, business-friendly language.

- Personality & Persona Engineering :

i. Translate business intents, user personas, and RCA objectives into concrete agent architectures and personality designs.

ii. Produce personality and behavior blueprints - communication style, decision boundaries, escalation thresholds, and safety constraints - for each in-scope persona.

iii. Operationalize prompting strategies (system prompts, tool instructions, reflection loops) so agents behave consistently and safely across channels.

- Multi-Agent GenAI & RCA Engineering :

i. Enhance the existing multi-agent system - signal triage, hypothesis generation, evidence gathering, recommendation synthesis, verification - preserving the established architecture.

ii. Implement evaluation and observability: hallucination detection, safety checks, reasoning traceability, and persona adherence.

iii. Ensure generated root-cause narratives and NBAs are auditable, explainable, and actionable for the target persona.

3. Required Experience & Proof Points :

- GenAI & Multi-Agent Systems :

i. 5-8+ years in AI/ML; 2-3+ years focused on GenAI and agentic systems.

ii. Shipped at least one production or late-stage pilot of a multi-agent GenAI system (e.g., orchestrated LLM agents for support, operations, or engineering workflows).

iii. Demonstrable experience with at least one agentic framework (LangChain / LangGraph, CrewAI, AutoGen, or equivalent) and with tool-calling / RAG patterns.

iv. Strong applied knowledge of LLM evaluation - curated test sets, human-in-the-loop review, regression testing across prompt/persona/tool changes.

- Personality & Persona Engineering :

i. Built persona-based assistants or role-specialized agents in an enterprise setting (e.g., ops copilot, contact-center coach, network/RCA assistant).

ii. Tangible persona artifacts: system prompt specifications, persona catalogs, behavior taxonomies, agent charters, or style guides.

iii. Experience designing tone, authority, and decision boundaries for agents serving multiple stakeholder personas (frontline, supervisors, engineers, execs).

- Root Cause Analysis & Observability :

i. Hands-on RCA experience in complex systems (network, IT ops, customer journeys, process failures) - ideally with automation/AI in the loop.

ii. Experience integrating AI agents with monitoring/observability (logs, metrics, traces, events) and ticketing/workflow tools.

iii. Documented improvements in MTTR, defect recurrence, or diagnostic throughput via AI/automation (with baselines and outcomes, even if anonymized).

- Enterprise Delivery & Self-Management :

i. Track record of owning a workstream inside a larger program - planning, stakeholder management, risk management, status reporting.

ii. Experience in regulated or high-oversight environments (telecom, financial services, healthcare, or large-scale consumer platforms).

iii. Strong communication skills: running design sessions, show-and-tells, and enablement workshops with mixed technical and non-technical audiences.

4. Core Technical Skills & Competencies :

- LLMs & GenAI :

i. Prompt and system-instruction design; role-conditioned generation.

ii. RAG architectures and retrieval design.

iii. Tool calling, workflow orchestration, and structured outputs.

iv. Multi-agent patterns: planner-worker, supervisor-specialist, debate/critique loops.

- Platforms & Languages :

i. Experience with one or more cloud AI platforms (Azure OpenAI, AWS Bedrock, Google Vertex, Anthropic APIs).

ii. Proficient in Python (preferred) and relevant libraries/frameworks for agentic systems, evaluation, and integration.

- AI Safety, Security & Governance :

i. Guardrails, PII handling, access control, auditability, and responsible AI practices suitable for an enterprise program.

ii. AI Safety & Policy-Bound Behavior

- RCA & Systems Thinking :

i. Solid grounding in RCA methodologies, systems thinking, and complex incident analysis.

ii. Ability to translate RCA patterns into agent behaviors and workflows - triage, hypothesis generation, evidence gathering, recommendation, verification.

- Consulting & Collaboration :

i. Problem framing, hypothesis-driven analysis, stakeholder alignment, and storytelling with data.

ii. Self-managing delivery: sprint planning, roadmap ownership, high-quality documentation.

5. Preferred Profile :

- 8-12 years total experience in AI/ML, software engineering, or data science, with 2-3+ years on GenAI and agentic systems.

- Prior experience in telecom, large-scale consumer tech, or similarly complex operational environments.

- Experience working inside or alongside enterprise AI/ML platforms, AI governance boards, or innovation labs.

- Prior exposure to agentic RAG RCA solutions and multi-agent orchestration for complex operational workflows.