Backend Engineer (Generative AI)

Role Overview

We are seeking an experienced Backend Engineer with strong expertise in Generative AI technologies to join our growing AI engineering team. This role focuses on designing, developing, and maintaining scalable backend services, AI orchestration frameworks, and cloud-native AI solutions that support enterprise-grade AI applications.

The successful candidate will contribute to the development of intelligent agent frameworks, Retrieval-Augmented Generation (RAG) solutions, AI marketplaces, and secure AI-enabled services while collaborating closely with product, frontend, and platform engineering teams.

Key Responsibilities

AI Orchestration and Agent Development

• Design and develop orchestration frameworks for AI agents using Python-based technologies and cloud-native AI services.
• Develop, integrate, and maintain reusable AI capabilities, agent workflows, and third-party API integrations.
• Support the onboarding and lifecycle management of agent capabilities and automation services.

Advanced RAG and Cloud Integration

• Design, implement, and optimise Retrieval-Augmented Generation (RAG) architectures.
• Integrate Large Language Models (LLMs), embedding models, and enterprise knowledge sources within cloud environments.
• Manage retrieval strategies, context management, and performance optimisation for AI applications.

Platform and Marketplace Development

• Design and develop backend services supporting AI capability marketplaces and knowledge-sharing platforms.
• Enable secure publishing, versioning, management, and governance of datasets, AI agents, document-based chat applications, and reusable AI capabilities.

Backend and API Engineering

• Architect, develop, and maintain scalable backend services and APIs.
• Design and manage relational database solutions, including PostgreSQL, to support application data and workflow management.
• Ensure high availability, performance, maintainability, and scalability of backend systems.

Vector Search and Data Engineering

• Design and optimise vector search, retrieval systems, and search infrastructure.
• Manage vector databases, search platforms, and indexing strategies to improve retrieval accuracy, relevance, and performance.

Agent Observability and Evaluation

• Implement monitoring, telemetry, and observability capabilities for AI applications and agent workflows.
• Develop evaluation frameworks to assess AI outputs, application performance, reliability, and quality.
• Support initiatives to improve model performance and reduce inaccurate or undesired outputs.

AI Security and Governance

• Implement security controls for AI applications, including access controls, data protection measures, content filtering, and secure integration practices.
• Ensure compliance with enterprise security, governance, privacy, and regulatory requirements.
• Support the responsible use of AI technologies through risk management and governance frameworks.

Data Pipelines and Platform Support

• Design and maintain data ingestion, transformation, and processing pipelines supporting AI applications and knowledge systems.
• Support data preparation workflows and integration with vector databases and enterprise data platforms.

Cross-Functional Collaboration

• Work closely with frontend engineers, designers, product teams, and platform engineers to deliver end-to-end AI-enabled solutions.
• Participate in architecture reviews, technical discussions, and continuous improvement initiatives.

Requirements

Qualifications and Experience

• Bachelor's Degree in Computer Science, Software Engineering, Information Technology, or a related discipline.
• At least 5 years of software engineering experience with strong expertise in backend development, API design, and distributed systems architecture.
• Hands-on experience building AI-enabled applications using frameworks such as LangChain, LlamaIndex, LangGraph, or equivalen