AI Data Scientist - Autonomous Network

Capgemini; Abingdon; On-site; GBP 70,000 - 110,000; Full time

Benefits offered by this job

Hybrid working model

Travel to client site

Job summary

Capgemini is seeking an AI/Data Scientist to apply data science, statistics, and ML to autonomous network intelligence. You will work with network telemetry, topology, and service data to build predictive insights and KPI models across RAN, Core, IP/MPLS, SD-WAN, and cloud domains.

You will collaborate with AI/LLM engineers, develop data pipelines, and ensure explainable, governed models for operational decision-making in a hybrid Newbury-based role.

Qualifications

• Experience in data science, telecom analytics, or AIOps analytics.
• Strong Python skills for data analysis, modelling, and automation.
• Strong knowledge of statistics, ML basics, feature engineering, and model evaluation.
• Experience with network KPIs, alarms, telemetry, inventory, topology, or service assurance data.
• Understanding of telecom network domains including RAN, Core, IP/MPLS, SD-WAN, Transport, Cloud, or OSS.
• Experience developing anomaly detection, fault analysis, predictive analytics, or KPI models.
• Experience with data aggregation, cleansing, enrichment, and data quality assessment.
• Experience with graph analytics, entity relationship mapping, or knowledge graph concepts.
• Understanding of LLMs and how structured data can support AI agents and RAG systems.
• Experience with BigQuery or similar data warehouse/analytics platforms.

Responsibilities

• Analyse large-scale telecom network datasets across RAN, Core, IP, Transport, SD-WAN, Cloud, OSS, and service domains.
• Develop KPI engineering models for network performance, service quality, fault behaviour, customer impact, capacity, and resilience.
• Build statistical and machine learning models for anomaly detection, fault prediction, root-cause analysis, degradation detection, and proactive assurance.
• Develop data aggregation, cleansing, enrichment, and feature engineering pipelines for network telemetry and OSS data.
• Support digital twin analytics using topology, inventory, configuration, service dependency, performance, and fault data.
• Develop graph analytics models for network topology, entity relationships, dependency mapping, service impact, and fault propagation.
• Work with AI/LLM engineers to provide high-quality features, embeddings, metadata, and contextual datasets for RAG and agentic AI systems.
• Define network data quality rules, correlation logic, and entity resolution methods.
• Create reusable analytical models for RAN, Core, IP/MPLS, SD-WAN, fixed, and cloud network KPIs.
• Support AIOps use cases such as alarm reduction, incident prioritisation, predictive maintenance, and automated root-cause analysis.
• Work with OSS and inventory teams to align data models with TMF SID concepts and TMF Open API structures.
• Use BigQuery or equivalent analytics platforms to process large-scale network data.
• Ensure models are explainable, measurable, governed, and suitable for operational decision‑making.

Skills

Python

Statistics

ML basics

KPI engineering

AIOps analytics

Data pipelines

Graph analytics

LLM understanding

BigQuery

Network KPI modelling

Tools

BigQuery

Graph APIs

Open API

TMF SID

Job description

Your Role

This role focuses on applying data science, statistics, machine learning, graph analytics, and KPI engineering to enable autonomous network intelligence. The AI Data Scientist will work with network telemetry, alarms, performance counters, inventory data, topology data, trouble tickets, service data, and digital twin models to develop analytical insights and predictive intelligence for autonomous network operations.

Key Responsibilities

• Analyse large-scale telecom network datasets across RAN, Core, IP, Transport, SD-WAN, Cloud, OSS, and service domains.
• Develop KPI engineering models for network performance, service quality, fault behaviour, customer impact, capacity, and resilience.
• Build statistical and machine learning models for anomaly detection, fault prediction, root-cause analysis, degradation detection, and proactive assurance.
• Develop data aggregation, cleansing, enrichment, and feature engineering pipelines for network telemetry and OSS data.
• Support digital twin analytics using topology, inventory, configuration, service dependency, performance, and fault data.
• Develop graph analytics models for network topology, entity relationships, dependency mapping, service impact, and fault propagation.
• Work with AI/LLM engineers to provide high-quality features, embeddings, metadata, and contextual datasets for RAG and agentic AI systems.
• Define network data quality rules, correlation logic, and entity resolution methods.
• Create reusable analytical models for RAN, Core, IP/MPLS, SD-WAN, fixed, and cloud network KPIs.
• Support AIOps use cases such as alarm reduction, incident prioritisation, predictive maintenance, and automated root-cause analysis.
• Work with OSS and inventory teams to align data models with TMF SID concepts and TMF Open API structures.
• Use BigQuery or equivalent analytics platforms to process large-scale network data.
• Ensure models are explainable, measurable, governed, and suitable for operational decision‑making.

Your Profile

• Experience in data science, machine learning, telecom analytics, network performance analytics, or AIOps analytics.
• Strong Python skills for data analysis, modelling, and automation.
• Strong knowledge of statistics, ML basics, feature engineering, and model evaluation.
• Experience working with network KPIs, alarms, telemetry, inventory, topology, or service assurance data.
• Understanding of telecom network domains including RAN, Core, IP/MPLS, SD-WAN, Transport, Cloud, or OSS.
• Experience developing anomaly detection, fault analysis, predictive analytics, or KPI models.
• Experience with data aggregation, cleansing, enrichment, and data quality assessment.
• Experience with graph analytics, entity relationship mapping, or knowledge graph concepts.
• Understanding of LLMs and how structured data can support AI agents and RAG systems.
• Experience with BigQuery or similar data warehouse/analytics platforms.

Required Technical Skills

• Python.
• Statistics and ML basics.
• Network KPI modelling.
• RAN, Core, IP, SD-WAN, and Transport KPI understanding.
• Fault analysis and anomaly detection.
• AIOps analytics.
• Data aggregation and data pipelines.
• KPI engineering and feature engineering.
• Inventory models.
• Fault correlation.
• TMF SID understanding.
• BigQuery or equivalent analytics platform.
• Graph APIs and graph analytics.
• Digital twin analytics.
• LLM understanding.

Preferred Certifications

• Google Cloud Data Engineer or Machine Learning Engineer.
• Azure Data Scientist or AWS Machine Learning certification.
• Databricks, Snowflake, or equivalent data platform certification.
• TM Forum SID, Open API, or Autonomous Networks training.

Nice-to-Have Qualifications

• Experience with telecom digital twin platforms.
• Experience with vector databases, embeddings, semantic search, or RAG.
• Experience with streaming data platforms such as Kafka, Pub/Sub, Flink, or Spark Streaming.
• Experience supporting closed-loop automation, predictive assurance, or self‑healing network use cases.
• Experience working with OSS systems, inventory platforms, assurance systems, and ticketing data.

If you're excited about this role but don't meet every requirement, we still encourage you to apply; your unique experience could be just what we need.

Make it real - what does it mean for you?

• Exposure to top global companies working with Capgemini (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

Capgemini is proud to be a Disability Confident Employer (Level 2) under the UK Government's Disability Confident scheme. As part of our commitment to inclusive recruitment, we will offer an interview to all candidates who:

• Declare they have a disability, and
• Meet the minimum essential criteria for the role.
• Please opt in during the application process.

Need to know

• 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 inclusive future is part of everyday life and will be part of your working reality. We have built a representative and welcoming environment, for everyone.