AI Full Stack Engineer (LLM / Agentic AI) | Contract

Overview

We are seeking a highly capable Full Stack Engineer to support the maintenance and enhancement of an existing AI-powered application while also building new generative AI solutions for enterprise use cases. This role will focus on both sustaining a production AI application and designing new solutions leveraging large language models (LLM), retrieval-augmented generation (RAG), and agentic AI frameworks.

The successful candidate will work closely with Project Managers, Solution Architects, and business stakeholders to deliver scalable, production-grade AI applications on AWS. This is a hands-on engineering role suited for candidates with solid software engineering fundamentals, experience in GenAI application development, and familiarity with modern full stack technologies.

Responsibilities

• Take over and maintain an existing AI-powered application through structured knowledge transfer, including understanding and documenting the current architecture, codebase, and system integrations.
• Perform ongoing application support activities including bug fixing, enhancements, incident resolution, performance tuning, and system stability improvements.
• Design, develop, and deploy end-to-end AI applications leveraging LLM,  retrieval-augmented generation (RAG), and agentic AI frameworks.
• Build MCP-based tool integrations and agentic workflows to connect AI applications with enterprise systems and business processes.
• Translate business requirements and stakeholder needs into scalable AI-powered solutions with robust backend and frontend architecture.
• Develop and integrate APIs, application logic, and user-facing features to support AI-driven use cases.
• Implement monitoring, observability, and evaluation mechanisms for AI model performance, prompt quality, and agent behaviour in production.
• Collaborate with cross-functional stakeholders including Project Managers, Architects, and business users to deliver production-ready solutions aligned to business outcomes.
• Contribute to application design, code quality, testing, deployment automation, and engineering best practices across the software development lifecycle.

Requirements

• Bachelor’s Degree in Computer Science or any related disciplnine.
• Minimum 2 years of hands-on experience in Full Stack Software Engineering with exposure to building and supporting production applications.
• Proven experience building AI agents or multi-agent systems using frameworks such as LangChain, LlamaIndex, LangGraph, AutoGen, or CrewAI.
• Experience with LLMs, RAG architectures, agentic design patterns, and production deployment of generative AI applications.
• Familiarity with MCP-based tool integrations, AI guardrails, application evaluation, and LLMOps practices.
• Good understanding of prompt engineering, model evaluation, AI observability tools (e.g. LangSmith), responsible AI, and AI governance.
• Solid software engineering fundamentals including clean code, testing, design patterns, REST API development, CI/CD, and containerisation.
• Proficiency in Python, TypeScript, React / Next.js, and Tailwind CSS.
• Experience working with relational and NoSQL databases, including schema design, query optimisation, and data management.
• Familiarity with vector databases and semantic search concepts for RAG-based applications.
• Hands-on experience with AWS, including services such as Lambda, API Gateway, S3, CloudWatch, and IAM.
• Experience with AWS Bedrock, including working with foundation models such as Claude and features such as Knowledge Bases, Agents, and Guardrails.
• Excellent communication skills with the ability to work closely with technical and non-technical stakeholders.