AI Backend Developer

BT Group; Bengaluru; Hybrid; INR 1,500,000 - 2,100,000; Full time

Job summary

BT Group seeks an experienced software engineer to drive AI-enabled transformation of Openreach scheduling and inventory platforms. You will design, deploy, and support AI agents, copilots, and automation workflows to improve efficiency and productivity.

You will build AI-driven scheduling, workforce optimization, and decision-support for large-scale environments using RAG, ReAct, prompt chaining, and memory frameworks, leveraging LLMs and cloud-native services across the SDLC.

Qualifications

• 4–7 years of software engineering experience with strong AI-enabled solutions.
• Hands-on work with Generative AI and Large Language Models (GPT, Claude, Gemini, etc.).
• Experience designing RAG architectures, ReAct, Prompt Chaining, Planner-Executor, and Chain-of- Thought prompting.
• Expertise in Machine Learning, Predictive Analytics, and Reinforcement Learning.
• Knowledge of Operations Research, Workforce Optimization, Scheduling, Route Optimization, and Simulation.
• Proficiency in Python and Java/Node.js for scalable backend AI services.
• Experience with APIs, Microservices, Cloud-native platforms, and enterprise integrations.
• Knowledge of Vector Databases like Pinecone, FAISS, Azure AI Search.
• Experience with Azure OpenAI, AWS Bedrock, or equivalent AI cloud platforms.
• Understanding of Model Context Protocol concepts and AI architecture.

Responsibilities

• Lead the technical transformation of scheduling and inventory platforms into AI-powered, cloud-native ecosystems.
• Design, develop, deploy, and support AI-powered agents, copilots, automation solutions, and intelligent workflows.
• Build AI-driven scheduling, workforce optimization, and decision-support for large-scale operations.
• Design and implement RAG, ReAct, Prompt Chaining, Planner-Executor, and other AI workflows.
• Develop AI-enabled services using LLMs and supporting technologies.
• Build and maintain APIs, microservices, and integrations between AI solutions and enterprise systems.
• Apply AI across the SDLC using tools like GitHub Copilot and other AI-native development tools.
• Develop and maintain prompt libraries, context management, and memory frameworks.
• Design optimization, routing, forecasting, and simulation models for workforce planning.
• Apply ML and Operations Research techniques to business challenges and improve performance.
• Monitor AI solution performance, reduce hallucinations, improve accuracy, latency, costs, and adoption.

Skills

AI-enabled solutions

Generative AI & LLMs

RAG architectures & prompts

Python & Java/Node.js

Cloud-native & microservices

APIs & enterprise integrations

Tools

Vector Databases

Azure AI/OpenAI/AWS Bedrock

Job description

Role & responsibilities

• Lead the technical transformation of Openreach scheduling and inventory platforms into AI-powered, cloud-native, scalable ecosystems that improve operational efficiency and engineering productivity.
• Design, develop, deploy, and support AI-powered agents, copilots, automation solutions, and intelligent workflow systems.
• Build next-generation AI-driven scheduling, workforce optimization, and decision-support capabilities for large-scale operational environments.
• Design and implement Retrieval Augmented Generation (RAG), ReAct, Prompt Chaining, Planner-Executor, and other agentic AI workflows.
• Develop AI-enabled services using Large Language Models (LLMs) and supporting technologies.
• Build and maintain APIs, microservices, and integrations between AI solutions and enterprise systems.
• Implement AI capabilities across the Software Development Lifecycle (SDLC) using AI-assisted development tools such as GitHub Copilot, Cursor, Amazon Q, and Kiro.
• Develop and maintain prompt libraries, reusable AI components, context management, and memory frameworks.
• Design workforce optimization, constraint-based scheduling, route optimization, recommendation engines, forecasting, and simulation models.
• Apply Machine Learning, Predictive Analytics, Reinforcement Learning, and Operations Research techniques to complex business challenges.
• Monitor AI solution performance and continuously improve accuracy, hallucination rates, task success rates, latency, operational costs, and user adoption.
• Ensure engineering excellence through security, DevSecOps, CI/CD, observability, reliability, scalability, and SRE best practices.
• Collaborate with architects, engineers, product teams, and business stakeholders to deliver AI initiatives and drive adoption of AI-enabled ways of working.

Skills & Experience

• 4-7 years of Software Engineering experience with strong expertise in AI-enabled solutions.
• Strong hands-on experience in Generative AI, Large Language Models (GPT, Claude, Gemini, etc.), Prompt Engineering, and Agentic AI solutions.
• Experience designing and implementing RAG architectures and AI design patterns including ReAct, Prompt Chaining, Planner-Executor, and Chain-of-Thought prompting.
• Expertise in Machine Learning, Predictive Analytics, and Reinforcement Learning.
• Strong knowledge of Operations Research, Workforce Optimization, Constraint-Based Scheduling, Route Optimization, Mathematical Modelling, and Simulation.
• Proficiency in Python and Java/Node.js with experience building scalable backend systems and AI services.
• Experience with APIs, Microservices Architecture, Cloud-native platforms, and Enterprise System Integrations.
• Knowledge of Vector Databases such as Pinecone, FAISS, Azure AI Search, or similar platforms.
• Experience with Azure AI Services, Azure OpenAI, AWS Bedrock, or equivalent AI cloud platforms.
• Understanding of MCP (Model Context Protocol) concepts and AI application architecture.
• Experience implementing AI capabilities within SDLC using AI-native development tools.
• Expertise in performance optimisation, high-performance system design, DevSecOps, CI/CD, observability, and Site Reliability Engineering (SRE).
• Experience building large-scale operational decision-support systems supporting workforce planning and optimization.