AI LLM Engineer - Autonomous Network

Responsibilities

• check_circle Design and develop LLM-based and agentic AI solutions for autonomous network operations.
• check_circle Build RAG frameworks using network documentation, alarms, topology, inventory, KPIs, trouble tickets, procedures, configuration data, and operational knowledge.
• check_circle Develop multi-agent workflows using LangChain, LangGraph, MCP, or similar frameworks.
• check_circle Implement vector search, semantic retrieval, graph-enhanced retrieval, and hybrid search patterns.
• check_circle Develop AI agents for fault diagnosis, root-cause analysis, KPI analysis, configuration recommendation, incident summarisation, and operational decision support.
• check_circle Build token-efficient prompting, context optimisation, caching, and response generation techniques.
• check_circle Integrate LLM solutions with OSS, AIOps, inventory, graph databases, vector databases, data pipelines, and automation platforms.
• check_circle Develop fault correlation, KPI modelling, predictive analytics, and closed-loop trigger logic.
• check_circle Implement safe AI workflows with human-in-the-loop approval, confidence scoring, explainability, and auditability.
• check_circle Optimise AI models and agent workflows for latency, cost, accuracy, and reliability.
• check_circle Support model evaluation, prompt evaluation, hallucination reduction, retrieval quality improvement, and grounding validation.
• check_circle Work with cybersecurity teams to implement LLM security, prompt injection protection, data leakage prevention, and access controls.
• check_circle Deploy AI services using Kubernetes, Docker, APIs, and cloud-native patterns.
• check_circle Experience in AI/ML engineering, data engineering, software engineering, or applied machine learning.
• check_circle Hands-on experience with LLMs, RAG, semantic search, or agentic AI systems.
• check_circle Strong Python programming skills.
• check_circle Experience with ML fundamentals, deep learning concepts, embeddings, transformers, and LLM architectures.
• check_circle Experience using LangChain, LangGraph, LlamaIndex, AutoGen, MCP, or similar AI frameworks.
• check_circle Experience with vector databases such as Pinecone, Weaviate, Milvus, Qdrant, ChromaDB, or equivalent.
• check_circle Experience with graph databases, knowledge graphs, or Graph APIs.
• check_circle Experience building data pipelines and integrating structured and unstructured data sources.
• check_circle Understanding of AIOps, fault correlation, KPI modelling, predictive analytics, or telecom network operations.
• check_circle Experience deploying AI services using Kubernetes, Docker, APIs, and cloud-native environments.
• check_circle Python.
• check_circle ML basics and deep learning.
• check_circle LLMs and transformers.
• check_circle LangChain, LangGraph, MCP, or similar frameworks.
• check_circle Vector databases and semantic search.
• check_circle Graph APIs and knowledge graphs.
• check_circle Data pipelines and data aggregation.
• check_circle Docker and Kubernetes.
• check_circle Fault correlation and KPI modelling.
• check_circle Predictive analytics and AIOps.
• check_circle Closed-loop triggers.
• check_circle Prompt engineering and context optimisation.
• check_circle AI observability and evaluation.
• check_circle Google Cloud AI/ML or Vertex AI certification.
• check_circle Azure AI Engineer or AWS Machine Learning certification.
• check_circle Databricks, BigQuery, or data engineering certification.
• check_circle Kubernetes certification.
• check_circle TM Forum Autonomous Networks or Open API certification.

Preferred qualifications

• Experience with Google Vertex AI, Gemini APIs, BigQuery, or equivalent platforms.
• Experience with telecom network data including RAN, Core, IP/MPLS, SD-WAN, OSS, alarms, KPIs, and inventory.
• Experience developing LLM agents for network operations, incident management, or service assurance.
• Experience with AI model optimisation, inference cost reduction, latency optimisation, and scalable AI serving.
• Exposure to top global companies working withCapgemini (145 of the Fortune 500 companies)
• Open access to digital learning platforms
• Active employee networks promoting diversity, equity and inclusion like OutFront, CapAbility or Women@Capgemini
• Declare they have a disability, and
• Meet the minimum essential criteria for the role.
• Please opt in during the application process.
• All roles will require a level of security clearance; BPSS OR Security Clearance OR Developed Vetting.
• Location: This is a permanent role with Capgemini, offering a hybrid working model. The client is based in Newbury and occasional travel to the client site will be required.
• You can bring your whole self to work. At Capgemini building an inclusivefuture is part of everyday life and will be part of your working reality. We havebuilt a representative and welcoming environment, for everyone.

About the company