M40 - Full Stack Engineer

Role Overview

We are seeking a Full Stack & AI Engineer to design, develop, deploy, and maintain secure, scalable, and high-performance applications across frontend, backend, cloud, and AI platforms. The role involves full-stack application development, maintenance of the Chatbook Application, and the development and integration of enterprise-grade AI solutions.

Key Responsibilities

Full Stack Application Development

• Design, develop, deploy, and maintain secure, scalable, and high-performance web applications across frontend, backend, and cloud platforms.
• Ensure application quality, performance, security, reliability, and maintainability through modern software engineering practices.
• Work in an Agile and DevOps-driven environment, applying CI/CD, automation, testing, and secure development practices.
• Collaborate with cross-functional teams to deliver reliable and production-ready software solutions.

Chatbook Application Maintenance

• Take ownership of the Chatbook Application following knowledge transfer.
• Provide ongoing application maintenance, enhancements, performance optimisation, troubleshooting, and incident resolution.
• Ensure application stability, reliability, and continuous improvement.

AI Solution Development & Integration

• Design and implement AI-powered solutions using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), agentic frameworks, and Model Context Protocol (MCP)-based integrations.
• Develop enterprise AI workflows and production-ready AI applications.
• Implement monitoring, observability, evaluation, and guardrails for AI solutions.
• Translate business requirements into scalable, secure, and production-ready AI solutions.

Requirements

Education

• Degree or Diploma in Computer Science, Computer Engineering, Electronics Engineering, Information Technology, or a related discipline.

AI & Agentic Engineering

• Hands-on experience building AI agents and multi-agent systems using frameworks such as LangChain, LlamaIndex, LangGraph, AutoGen, or CrewAI.
• Strong understanding of agentic design patterns, including planning, tool use, memory, and reflection.
• Experience with MCP-based tool integrations and maintaining GenAI and agentic applications in production environments.
• Experience implementing AI guardrails, application evaluation, and production monitoring.
• Knowledge of LLMOps practices, including prompt management, model evaluation, LLM observability tools such as LangSmith or similar platforms, AI governance, and responsible AI principles.

Software Engineering

• Strong software engineering fundamentals, including clean code, design patterns, automated testing, REST API development, containerisation, container orchestration, CI/CD pipelines, and Git-based version control.
• Proficiency in Next.js, React, Python, TypeScript, and Tailwind CSS.
• Strong experience with relational and NoSQL databases, including query optimisation, schema design, and data management.
• Familiarity with vector databases for RAG and semantic search.
• Knowledge of secure software development practices, including authentication and authorisation, API security, secrets management, and OWASP best practices.

Cloud & Infrastructure

• Hands-on experience with AWS cloud services, including Lambda, API Gateway, S3, CloudWatch, and IAM.
• Experience with AWS Bedrock for accessing and orchestrating foundation models such as Anthropic Claude.
• Familiarity with AWS Bedrock capabilities such as Knowledge Bases, Agents, and Guardrails for production-grade generative AI applications.
• Experience developing and deploying applications on Government Commercial Cloud (GCC) is an advantage.