Senior Software Engineer (Fullstack + GenAI) - VOIS

Who we are

VOIS (Vodafone Intelligent Solutions) is a strategic arm of Vodafone Group Plc, creating value for customers by delivering intelligent solutions through Talent, Technology & Transformation.

As the largest shared services organisation in the global telco industry with 30,000 FTE, our portfolio of next-generation solutions and services are designed in partnership with customers across Vodafone Group, local markets, and partner markets to simplify and drive growth. With our strategic partner Accenture, we work alongside our Vodafone customers, other Telco and tech companies to drive transformation, meet the challenges of our industry and ensure we stay relevant and resilient. This partnership is a unique, industry-first model which brings together the best of in-house and 3rd party capability.

We work with customers across 28 countries from 10 VOIS locations: Albania, Egypt, Hungary, India, Romania, Spain, Turkey, UK, Germany, Ireland, and with a network of teams in Czech Republic, Italy, Greece, and Portugal.

#VOIS #BeUnrivalled #CreateTheFuture

About this Role

We are seeking a senior full-stack engineer with strong end-to-end software engineering experience and practical experience delivering enterprise Generative AI (GenAI) applications. You will combine modern React and TypeScript frontend development with Python backend engineering, Large Language Model (LLM) integration and cloud-native delivery.

You will bring 5-8+ years of professional software development experience, including strong full-stack expertise, alongside at least 1-2 years of hands-on experience developing GenAI/LLM-powered applications, preferably in production environments.

The role provides end-to-end ownership across solution design, implementation, testing, deployment and production support, with a focus on scalable enterprise applications, microservices, RESTful APIs, Retrieval-Augmented Generation (RAG) and Microsoft Azure technologies.

What you’ll do

• Design and develop scalable, enterprise-ready full-stack GenAI applications.
• Build and maintain Python backend services, microservices and RESTful APIs using frameworks such as FastAPI or Django.
• Develop modern, responsive and reusable web interfaces using React.js, TypeScript/JavaScript, HTML5 and CSS3.
• Integrate frontend applications with backend APIs, including state management, authentication and performance optimisation.
• Integrate LLMs using Azure OpenAI, OpenAI APIs or equivalent platforms.
• Design and implement RAG pipelines using embeddings, vector databases, semantic or hybrid search and document retrieval.
• Develop prompt engineering approaches, structured outputs, LLM orchestration, tool/function calling and AI-agent workflows.
• Build reusable GenAI components and shared platform capabilities.
• Apply asynchronous programming, background processing and external API integrations where appropriate.
• Work with SQL and NoSQL databases while optimising application performance, logging and error handling.
• Implement authentication and authorisation using technologies and standards including OAuth 2.0, OpenID Connect and JWT.
• Ensure secure API development, data protection, application reliability and production readiness.
• Develop unit, integration and automated tests.
• Use Docker, Git and CI/CD pipelines to support cloud-native deployment.
• Monitor and optimise LLM response quality, latency, reliability and token/cost efficiency.
• Collaborate with Solution Architects, DevOps engineers, product owners and cross-functional engineering teams.
• Contribute to technical design decisions and mentor junior engineers.
• Support production troubleshooting, optimisation and continuous improvement.

Who you are

You have:

• 5-8+ years of professional software development experience, with strong full-stack expertise.
• At least 1-2 years of hands-on GenAI/LLM application development experience, preferably involving production deployments.
• Proven experience designing, developing and deploying scalable enterprise applications.
• Strong Python expertise, preferably using FastAPI or Django.
• Strong experience designing and developing RESTful APIs and microservices.
• Experience with asynchronous programming, background processing and API integrations.
• Experience with SQL and NoSQL databases, performance optimisation, logging and error handling.
• Strong hands-on experience with React.js and TypeScript/JavaScript.
• Experience developing responsive, reusable and maintainable UI components using modern frontend practices.
• Experience with frontend-to-backend API integration, state management, authentication and performance optimisation.
• Hands-on experience integrating LLMs through Azure OpenAI, OpenAI APIs or equivalent platforms.
• Practical experience developing Retrieval-Augmented Generation (RAG) solutions.
• Knowledge of embeddings, vector databases, semantic/hybrid search and document retrieval.
• Experience with prompt engineering, structured outputs and LLM orchestration.
• Familiarity with LangChain, LangGraph or LlamaIndex, including tool/function calling and AI-agent workflows.
• Understanding of LLM evaluation, response quality, latency and token/cost optimisation.
• Hands-on experience with Microsoft Azure, or strong experience with a comparable cloud platform.
• Familiarity with Azure AI Search, Azure OpenAI, Cosmos DB, Blob Storage, App Service and Container Apps.
• Experience with Docker, Git, CI/CD pipelines, monitoring and cloud-native architecture.
• Good understanding of software architecture, design patterns and clean-code principles.
• Experience with unit, integration and automated testing.
• Knowledge of OAuth 2.0, OpenID Connect and JWT.
• Experience with secure API development, data protection, production troubleshooting and reliability.
• Analytical thinking, sound judgement and effective problem-solving skills.
• The ability to own delivery independently and communicate proactively.
• Experience collaborating with architects, product owners and cross-functional engineering teams.
• The ability to mentor junior engineers and contribute to technical design decisions.
• Comfort working in Agile environments across multiple business priorities.

Experience in the following areas would also be valuable:

• Azure AI Document Intelligence and document ingestion pipelines.
• Enterprise knowledge bases and conversational AI applications.
• Agentic AI architectures, Model Context Protocol (MCP) and multi-agent workflows.
• Real-time applications, WebSockets and streaming APIs.
• Kubernetes, Terraform and infrastructure as code.
• Google Cloud Platform (GCP) or multi-cloud architectures.
• LLM evaluation frameworks, observability and guardrails.

Not a perfect fit?

Concerned you may not meet every requirement? Vodafone is committed to creating an inclusive workplace where everyone can thrive. If you are excited about this role but your experience does not align exactly with every aspect of the job description, you are encouraged to apply. You may be the right candidate for this or another opportunity, and the recruitment team will support you in exploring where your skills fit best.

What's in it for you

• The opportunity to work on enterprise-scale GenAI applications covering the full technology stack, from modern web experiences to LLM-powered backend capabilities.
• End-to-end engineering ownership across solution design, development, testing, deployment, optimisation and production support.
• Practical exposure to cloud-native architectures and Microsoft Azure AI technologies.
• Opportunities to collaborate with Solution Architects, DevOps engineers, product owners and cross-functional engineering teams.
• The opportunity to contribute to reusable GenAI capabilities, technical design decisions and engineering practices.

What skills you will learn

• Enterprise GenAI application architecture and production deployment.
• Advanced RAG, semantic/hybrid search, embeddings and enterprise document retrieval.
• LLM orchestration, tool/function calling and agentic AI workflows.
• Azure OpenAI, Azure AI Search, Cosmos DB, Blob Storage and Azure cloud-native services.
• LLM evaluation, observability, guardrails, latency optimisation and token/cost management.
• Reusable GenAI platform capabilities and enterprise knowledge solutions.
• Secure, scalable and reliable full-stack AI engineering.

VOIS Equal Opportunity Employer Commitment

Vodafone recognises and celebrates the value of diversity in building a workforce that reflects the customers and communities it serves. No form of discrimination is tolerated. This includes, but is not limited to, discrimination based on race, colour, age, veteran status, gender, pregnancy, maternity or parental status, ethnicity, disability, religion or belief, political affiliation, trade union membership, nationality, citizenship, indigenous status, medical condition, HIV status, neurodiversity, social origin, cultural background, marital or civil partnership status, or socio-economic background.

Join Us

At Vodafone, we’re working hard to build a better future. A more connected, inclusive and sustainable world. As a dynamic global community, it's our human spirit, together with technology, that empowers us to achieve this.

We challenge and innovate in order to connect people, businesses, and communities across the world. Delighting our customers and earning their loyalty drive us, and we experiment, learn fast and get it done, together.

With us, you can truly be yourself and belong, share inspiration, embrace new opportunities, thrive, and make a real difference.

Alert

Apply for Vodafone jobs only through the official Vodafone Careers website to avoid job scams and fraud.

Follow us on social media and #StayConnected

• LinkedIn: https://www.linkedin.com/company/vois/
• Facebook: https://www.facebook.com/voisglobal
• Instagram: https://www.instagram.com/voisglobal/
• You can also chat with our employees to learn more about our projects: https://lnkd.in/dpkrcvR2