Job Description
About Accenture Data & AI
The beginning of a new Data & AI decade that will reshape work and society is underway. Accenture is stepping boldly into this future with a clear strategy and purpose: to help clients optimise and reinvent their businesses with data and AI — backed by a $3 billion investment and a commitment to industry-defining work.
With over 45,000 professionals dedicated to Data & AI, Accenture's Data & AI organisation brings together Experienced Innovation, Strategic Investment, Exceptional Talent, and a Power Ecosystem to deliver outcomes at the frontier of what is possible.
About The Role
Accenture is establishing a dedicated Agentic AI Ninja Team — a group of highly experienced engineers tasked with solving the most complex challenges at the frontier of autonomous AI. This is a technical leadership position for engineers who have designed, built, and operated production-grade agentic systems at enterprise scale.
The Associate Manager will be responsible for the full delivery lifecycle of agentic AI applications: from system architecture and agent design through to deployment, evaluation, and production observability. Candidates will be expected to bring deep hands-on experience with autonomous agent frameworks, multi-agent orchestration, advanced retrieval architectures, and enterprise-grade integration — not proof-of-concept or prototype experience, but systems that have operated under real business conditions with real consequences.
This role also carries a technical leadership responsibility: guiding engineers, setting delivery standards, and owning the quality of output across fast-moving, high-visibility client engagements within Accenture's Data & AI practice.
Position Responsibilities
Agentic System Design and Delivery
Architect and deliver production-grade autonomous AI systems — agents that plan, reason, invoke tools, recover from failures, and integrate with enterprise backends across cloud platforms.
Select and apply appropriate reasoning patterns (ReAct, Chain-of-Thought, Tree-of-Thought, Plan-and-Execute, Reflexion) based on task complexity, latency requirements, and verifiability needs.
Author structured agent specifications using spec-driven development practices; apply AI-assisted engineering tooling (Claude Code, Codex) to accelerate delivery without compromising rigour.
Design and maintain prompt architecture for production agents — system prompt structure, few-shot example design, structured output schemas, prompt versioning, and A/B testing of prompt changes as production artefacts.
Agent Harness and Orchestration
Design and implement the agent harness: agent instantiation, persona and instruction loading, tool binding, memory initialisation, and lifecycle management from invocation to termination.
Architect multi-agent orchestration topologies — supervisor/worker hierarchies, event-driven graphs, parallel execution — with defined A2A handoff contracts, shared state schemas, and structured escalation paths.
Configure the LLM gateway and model routing layer — directing agent calls by task type, latency, cost, and capability — using provider-agnostic abstraction (LiteLLM or equivalent) across LLM providers.
Tool Layer, Context, and Memory
Design, build, and maintain MCP servers exposing enterprise systems, APIs, databases, and SaaS platforms as agent-accessible tools — with robust schema design, error handling, idempotency, and retry logic.
Translate business processes into agent-executable skills, structured instructions, and reusable workflows — bridging the gap between business requirements and agent implementation.
Build context engineering pipelines — assembling the right information into the agent context window across multi-turn and long-running tasks, with explicit management of context budget and retrieval triggers.
Implement memory architectures — episodic, working, and long-term — using appropriate backends (vector stores, relational databases, cache layers) matched to each agent use case.
Knowledge Layer and Engineering
Design RAG pipelines for agentic contexts: hybrid search, semantic re-ranking, late chunking, multi-vector retrieval, and metadata filtering; manage the full lifecycle from ingestion through quality evaluation.
Build MCP-connected knowledge sources exposing structured and unstructured data assets as governed, agent-accessible tools.
Implement Text-to-SQL capabilities — prompt-to-query translation, schema grounding, query validation, and safe execution against live enterprise databases.
Integrate Elasticsearch as a retrieval backend: full-text search, BM25 scoring, faceted filtering, and hybrid semantic-lexical strategies.
Design knowledge graph and ontology layers providing agents with structured representations of domain entities and relationships for precise reasoning over interconnected enterprise knowledge.
Agent Ops, Registry, and Observability
Operate and maintain production agentic systems using AgentOps, LLMOps, and DevOps practices — CI/CD pipelines for agent code and prompt changes, automated evaluation gates, and deployment strategies (blue/green, canary) across environments.
Manage an agent and asset registry — versioned catalogue of agents, tools, skills, prompts, and workflows — enabling reuse, governance, and controlled promotion across development, staging, and production.
Define and implement agent evaluation frameworks: golden dataset construction, LLM-as-judge pipelines, tool-call accuracy measurement, trajectory evaluation, and faithfulness scoring.
Build agent testing suites distinct from evals — unit testing agents with mocked tools, integration testing multi-agent handoffs, and simulation environments for pre-production scenario testing.
Design HITL feedback capture: structuring human corrections and approvals as refinement signal for continuous improvement.
Build production observability from day one — distributed tracing, token-level cost tracking, latency profiling, failure logging, and drift detection.
Trust, Safety, and Responsible AI
Implement guardrail frameworks (NeMo Guardrails, LlamaGuard, or equivalent) for input and output validation, content filtering, and enforcement of agent behavioural boundaries.
Defend against prompt injection in agents that consume external content — documents, emails, web pages — and scope agent identity and credentials to the minimum required for each task.
Implement PII detection and redaction in agent inputs and outputs; design immutable audit trails of agent decisions and tool calls for compliance and forensic purposes.
Define blast radius controls and human-in-the-loop approval gates; ensure autonomous systems operate within governance boundaries agreed with the client.
Technical Leadership and Delivery
Remain an active, hands-on engineer — writing production code, contributing directly to complex technical problems, and setting the standard for engineering quality through personal example.
Own technical design decisions across agentic workstreams — produce architectural documentation, lead design reviews, and resolve engineering escalations.
Build and maintain agentic application frontends: streaming responses for long-running tasks, intermediate output display, transparent reasoning UX, and error and escalation interfaces.
Conduct code reviews and enforce engineering standards across the full stack — Python backend, frontend, cloud-native infrastructure, and DevOps/AgentOps/LLMOps pipelines.
Lead delivery in agile environments with stakeholder visibility; manage scope, quality, and technical risk. Support incident analysis for production agentic systems.
Core Requirements
3+ years building LLM-based applications in production — real users, real data, real operational accountability.
2+ years designing and deploying agentic AI systems in production — agents that reason, invoke tools, and operate with meaningful autonomy.
Hands-on experience with at least one agent orchestration framework (LangGraph, AutoGen, CrewAI, Semantic Kernel, AWS Strands, or equivalent) including harness configuration, A2A coordination, and production deployment.
Demonstrated experience across the Agent Development Lifecycle: specification, prompt architecture, harness build, tool and MCP integration, skills and workflow design, evaluation, deployment, and iterative refinement.
Proven track record deploying agents at scale in production — with measurable business value: automation rates, cycle time reduction, cost savings, or quality improvement attributable to the agentic system.
Proven experience deploying complex software systems in production environments — with demonstrable results; deep understanding of what it takes to make systems reliable at scale.
Experience with DevOps, AgentOps, and LLMOps practices: CI/CD for agent code and prompts, automated evaluation gates, deployment strategies, agent and asset registry management, and production operations.
Experience with knowledge layer engineering: RAG pipeline design, MCP-connected knowledge sources, Text-to-SQL, Elasticsearch, and knowledge graph or ontology implementation.
5+ years full stack engineering: Python backend and a frontend framework (React, Angular, or Node.js); active hands-on capability across the stack.
5+ years cloud-native development on AWS, Azure, or GCP — containerised workloads, managed services, CI/CD, and infrastructure as code.
3+ years technical leadership: design ownership, code review, engineer mentoring, and delivery accountability.
Experience on complex digital transformation programmes — multi-workstream, client-facing, with senior stakeholder exposure.
4+ years experience in classical AI/ML, data engineering, or advanced analytics — building and integrating intelligent systems in production environments.
Bachelor's degree in a related field, or equivalent work experience. A Master's degree in Computer Science, AI, or a related discipline is highly valued.
Additional Skills
Experience with reasoning pattern selection and implementation (ReAct, CoT, ToT, Plan-and-Execute) in production agent systems.
Experience with prompt versioning, A/B testing, and prompt change management as an engineering discipline.
Experience building MCP servers and translating business processes into agent-executable skills, instructions, and reusable workflows.
Experience designing and managing an agent asset registry — versioned catalogue of agents, tools, prompts, and workflows across environments.
Experience with knowledge graph design and ontology modelling — graph databases (Neo4j or equivalent), SPARQL, or RDF-based knowledge representation.
Experience building agent testing suites: mocked-tool unit tests, multi-agent integration tests, and simulation environments.
Experience implementing guardrail frameworks and prompt injection defences for production autonomous systems.
Experience with agent identity and access scoping, PII redaction pipelines, and audit trail design for compliance.
Experience with FinOps for agentic systems: token budget design, cost-per-task tracking, and model selection trade-offs.
Experience with multi-LLM routing and provider-agnostic model abstraction across cost, latency, and capability dimensions.
Proficiency with AI-assisted development tooling (Claude Code, GitHub Copilot, Codex) as an active part of the engineering workflow.
Experience integrating agentic systems with enterprise platforms (SAP, Salesforce, ServiceNow) via APIs or MCP.
