Production AI Agentic Engineer — Senior Consultant

Accenture

Greater London

In loco

GBP 120.000 - 170.000

Tempo pieno

2 giorni fa

Candidati tra i primi

Generatore di candidature

Ricevi una risposta da questo datore di lavoro — un curriculum e una lettera di presentazione personalizzati, che corrispondono esattamente a ciò che sta cercando.

Supera i filtri ATS

Descrizione del lavoro

Accenture in London and Birmingham is seeking an experienced AI Engineer to design and deploy production-grade agentic systems. You will own end-to-end architecture, from multi-agent orchestration to observability, and collaborate with client teams to move beyond pilots into production.

The role emphasizes hands-on work with LangGraph/CrewAI/AutoGen, OpenAI/Anthropic/Vertex AI integrations, and robust MLOps practices.

Competenze

Extensive software engineering experience in production environments.
Hands-on experience designing and deploying agentic AI solutions in a production environment.
Experience with agentic orchestration frameworks: LangGraph, CrewAI, AutoGen.
Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code.
RAG pipeline ownership: embeddings, chunking strategy, vector databases, and context engineering.
LLMOps fundamentals: eval harness design, prompt versioning, and production observability.
Cloud-native engineering: Kubernetes, Docker, microservices, serverless, CI/CD, and IaC.
Strong Python; Java or equivalent backend language; production debugging and observability experience.

Mansioni

Design and build production-grade agentic systems end-to-end.
Build and own RAG pipelines: embeddings, chunking, vector search, context engineering.
Integrate and abstract across multiple LLM providers with routing and cost management.
Implement LLMOps in production: eval harnesses with real quality metrics and observability.
Embed with client engineering teams to prototype and deploy agentic solutions.
Build reusable patterns, accelerators, and playbooks for future engagements.
Define and use metrics to measure agent accuracy, latency, safety, and cost.