AI Backend Developer

About BT Group

BT Group stands as the premier telecommunications organization in the UK, managing renowned brands such as BT, EE, Openreach, and Plusnet. Their mission is straightforward yet ambitious: to connect people and businesses for the greater good. The group caters to a diverse clientele including consumers, enterprises of all sizes, public sector entities, and other communication providers. BT Group's main function is to establish strategic direction, unlock value, and foster conditions that enable its brands and businesses to flourish. After completing an intensive phase of fibre infrastructure investments, the focus has shifted to operational simplification, leveraging technology and AI to enable smarter workflows, and reorganizing to enhance customer service and achieve sustained growth. The group also oversees strategy, policy, branding, capital distribution, and transformation initiatives to maximize organizational performance.

Role Overview

The position involves spearheading the transformation of Openreach's scheduling and inventory management systems into AI-enhanced, cloud-native, and scalable platforms aimed at boosting operational efficiency and engineering productivity.

Key Responsibilities

• Lead redevelopment of Openreach scheduling and inventory platforms using AI-driven, cloud-native approaches to improve efficiency and productivity.
• Design, develop, deploy, and maintain AI-powered agents, copilots, automation tools, and intelligent workflows.
• Create advanced AI-based scheduling, workforce optimization, and decision-support capabilities for large-scale operations.
• Implement Retrieval Augmented Generation (RAG) architectures and agentic AI workflows such as ReAct, Prompt Chaining, and Planner-Executor.
• Develop AI services leveraging Large Language Models (LLMs) and associated technologies.
• Build and sustain APIs, microservices, and enterprise system integrations for AI solutions.
• Incorporate AI capabilities into the software development lifecycle by utilizing AI-assisted coding tools like GitHub Copilot, Cursor, Amazon Q, and Kiro.
• Maintain and develop prompt libraries, reusable AI modules, context management, and memory systems.
• Design models for workforce optimization, constraint-based scheduling, route optimization, recommendation systems, forecasting, and simulations.
• Use Machine Learning, Predictive Analytics, Reinforcement Learning, and Operations Research methods to address complex business challenges.
• Continuously monitor and enhance AI model performance focusing on accuracy, hallucination rates, latency, cost-efficiency, and adoption rates.
• Ensure engineering best practices including security, DevSecOps, CI/CD pipelines, observability, scalability, reliability, and Site Reliability Engineering (SRE).
• Collaborate closely with architects, engineers, product managers, and business stakeholders to successfully deliver AI projects and foster adoption of AI-driven workflows.

Required Skills and Experience

• Between 4 to 7 years of experience in software engineering with a specialization in AI-powered solutions.
• Deep practical knowledge of Generative AI, Large Language Models (such as GPT, Claude, Gemini), Prompt Engineering, and agentic AI frameworks.
• Proficiency in designing and deploying RAG architectures and AI design patterns including ReAct, Prompt Chaining, Planner-Executor, and Chain-of-Thought prompting.
• Strong foundation in Machine Learning, Predictive Analytics, and Reinforcement Learning.
• Expertise in Operations Research techniques, workforce optimization, constraint-based scheduling, route optimization, mathematical modeling, and simulation.
• Programming skills in Python and Java/Node.js for developing scalable backend and AI services.
• Experience with building APIs, microservices, cloud-native platforms, and integrating enterprise systems.
• Familiarity with vector databases like Pinecone, FAISS, Azure AI Search, or similar tools.
• Practical experience with cloud AI platforms such as Azure AI Services, Azure OpenAI, AWS Bedrock, or equivalents.
• Knowledge of Model Context Protocol (MCP) concepts and AI application architectures.
• Experience embedding AI functionalities into the software development lifecycle using AI-native development tools.
• Skilled in performance tuning, designing high-performance systems, as well as practices related to DevSecOps, CI/CD, monitoring, and Site Reliability Engineering.
• Demonstrated experience developing scalable operational decision-support systems for workforce management and optimization.

Eligibility

Applicants should hold a B.Tech or B.E. degree in any specialization.