Backend Engineer - AI Native

The core responsibilities for the job include the following:

Backend Engineering and Architecture:

• Design and implement low-latency, high-availability, and performant backend services and APIs that power AI-enabled products.
• Be the architect for your module; own the design, scalability, and reliability of backend systems end to end.
• Write reusable, testable, and efficient code; enforce engineering best practices across the team.
• Integrate user-facing elements developed by front-end developers with robust server-side logic and AI-powered workflows.
• Implement security, data protection, and compliance standards across all backend services.
• Integrate multiple data sources, databases, and third-party systems into unified, scalable backend architectures.

AI-Native Development:

• Build, maintain, and optimise AI-native backend applications leveraging Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents, orchestration frameworks, and modern AI platforms.
• Design and implement robust data pipelines, vector databases, embedding strategies, knowledge retrieval systems, and model evaluation frameworks.
• Develop scalable backend workflows and integrations that automate business processes and deliver measurable AI-driven value.
• Implement observability, monitoring, prompt management, testing pipelines, and guardrails to ensure AI system quality, reliability, and compliance.
• Optimise AI application performance, latency, scalability, and cost efficiency across cloud environments.
• Evaluate, experiment with, and integrate new AI models, tools, and frameworks to continuously enhance product capabilities.

Requirements:

• 4+ years of experience in backend software engineering, with a strong focus on microservices design and implementation.
• Hands-on experience building AI/ML or generative AI applications using technologies such as OpenAI, Anthropic, Gemini, Azure AI, LangChain, LlamaIndex, CrewAI, AutoGen, or similar frameworks.
• Strong proficiency in Python (mandatory); familiarity with TypeScript, Java, or Go is a plus.
• Experience implementing RAG architectures, vector databases, embeddings, semantic search, prompt engineering, and AI evaluation frameworks.
• Deep understanding of Large Language Models (LLMs), AI agents, model orchestration, and modern AI development practices.
• Solid understanding of software architecture, APIs, microservices, distributed systems, and system integrations.
• Strong grasp of algorithms, problem-solving, and fundamental design principles behind scalable applications.
• Experience working with AWS, Azure, or GCP and deploying AI workloads in production environments.