Full Stack Engineer (Gen AI)

We are seeking a talented and versatile Full Stack Engineer to join our Gen AI team. In this role, you will be responsible for developing and maintaining both front-end and back-end components of our Gen AI applications, including RAG chatbots, agentic AI systems, and film classification platforms. Your expertise in full stack development, cloud-based AI services, and quality assurance will be crucial in bringing cutting-edge AI technologies—including autonomous AI agents—to life through intuitive and efficient web applications.

Key Initiatives

As a Full Stack Engineer (Gen AI), you will initially support two key projects:

AI Assistant Platform

• Built on AWS Bedrock with multi-cloud integration (GCP and Azure)
• Supports Gemini and OpenAI models
• Frontend development using TypeScript and Next.js
• Multi-cloud architecture requiring seamless integration across AWS, GCP, and Azure services

Film Classification System

• Built on GCP's Agentic framework
• Utilises Gemini models with multi-agent architecture
• Backend development using Python
• Advanced agentic AI workflows for automated film content analysis

Key Responsibilities

Development Responsibilities:

• Full Stack Development: Design, develop, and maintain both front-end and back-end components of Gen AI applications, ensuring seamless integration between user interfaces and LLM-powered backends.
• Cloud-Native Development: Architect and implement cloud-native solutions leveraging AWS, GCP, and Azure services, with particular focus on AI/ML services across these platforms.
• LLM Integration: Implement APIs and services to integrate Large Language Models (including AWS Bedrock, Azure OpenAI, and GCP's Gemini) into web applications, focusing on efficient data flow and real-time processing of model outputs.
• Agentic AI Development: Build and maintain autonomous AI agent systems capable of multi-step reasoning, planning, and decision-making. Implement agent orchestration frameworks that enable AI agents to use tools, access external APIs, and execute complex workflows.
• Agent Tool Integration: Develop and integrate tool-calling capabilities for AI agents, enabling them to interact with external systems, databases, and APIs to accomplish user-defined goals autonomously.
• User Interface Design: Create intuitive and responsive user interfaces for Gen AI applications, with a focus on enhancing user experience in chatbot interactions, agentic AI workflows, and film classification interfaces.
• Database Management: Design and maintain databases to store and retrieve data efficiently for Gen AI applications, including user interactions, model outputs, agent execution logs, and system state management.
• Performance Optimisation: Optimise application performance, focusing on reducing latency in LLM-powered features, agent execution times, and ensuring smooth user experiences even under high loads.
• Security Implementation: Implement robust security measures to protect sensitive data and ensure compliance with data protection regulations, particularly for AI-driven applications handling user inputs and autonomous agent actions.
• DevOps and Deployment: Participate in CI/CD pipeline setup and maintenance, ensuring smooth deployment of Gen AI applications across different cloud environments.
• Documentation: Maintain comprehensive documentation for codebases, APIs, agent workflows, and system architectures to facilitate knowledge sharing and future development.

Testing & Quality Assurance Responsibilities:

• LLM Testing & Validation: Design and execute comprehensive test cases to evaluate the accuracy, reliability, and performance of LLMs integrated into Gen AI applications. Verify that model responses are relevant, contextually appropriate, and factually correct.
• Hallucination Identification: Focus on detecting hallucinations where the model produces false or fabricated information, ensuring these are promptly identified and addressed. Help refine models to reduce these occurrences.
• Accuracy & Quality Assurance: Assess the accuracy of model outputs, especially in high-precision contexts like chatbot conversations or film classification, ensuring that LLMs produce responses that are both relevant and correct according to predefined business logic.
• Test Automation for LLMs: Implement automated testing for common use cases, edge cases, and regression tests, especially focusing on cases that tend to trigger hallucinations or inaccuracies in the model's responses.
• Functional & Non-Functional Testing: Evaluate the LLM's functionality in different scenarios to check if it meets functional requirements. Perform non-functional testing like performance, load, and stress tests to assess the scalability of LLMs when handling high loads or multiple queries.
• Testing and Debugging: Develop and execute unit tests, integration tests, and end-to-end tests for both front-end and back-end components, with a focus on identifying and resolving issues related to LLM integrations, agent behaviour, hallucinations, and inaccurate outputs.
• Bug Reporting & Issue Resolution: Identify and document bugs related to hallucinations, inaccurate outputs, or unexpected model behaviours. Work closely with data scientists and developers to resolve issues and refine models.
• Regression Testing: Ensure that model updates, fine-tuning, or new training data do not introduce regressions or increase hallucinations and inaccuracies. Perform retesting of fixed issues and reassess model accuracy after updates.

Required Skills & Qualifications

Development Skills:

1. Strong experience in AWS cloud services, including:
• AWS Bedrock for foundation model deployment
• Core AWS services (EC2, S3, Lambda, API Gateway, etc.)
• AWS security and IAM best practices
2. Working knowledge of GCP and Azure, with ability to:
• Navigate and utilise services across multiple cloud platforms
• Implement multi-cloud integration strategies
• Understand platform-specific AI/ML services
3. Hands-on experience with cloud-based AI services, particularly:
• AWS Bedrock for foundation model access and deployment
• Azure OpenAI Service for GPT model integration
• GCP's Gemini models and Vertex AI platform
4. Strong full stack development experience, with proficiency in:
• Frontend: TypeScript, Next.js, React, or similar modern frameworks
• Backend: Python and Node.js
• RESTful API design and implementation for AI model integration
5. Proficiency in version control systems (e.g., Git) and experience with collaborative development workflows.
6. Strong problem-solving skills and ability to optimise application performance, especially in the context of AI-powered features and cloud-native architectures.
7. Knowledge of web security best practices and experience implementing secure authentication and authorisation systems.
8. Understanding of asynchronous programming and event-driven architectures for handling agent workflows and long-running AI tasks.

Testing & Quality Assurance Skills:

• Experience with test-driven development and automated testing frameworks.
• Test automation skills using tools (e.g., Selenium, PyTest, custom AI test frameworks) for automating LLM tests, especially those designed to catch inaccuracies or hallucinations in model outputs.
• Understanding of AI-specific testing methodologies, including how to measure and test for accuracy, hallucinations, and relevant responses in natural language processing (NLP) tasks.
• Strong programming skills in Python for developing test scripts and analysing the results of LLMs.
• Ability to report issues related to hallucinations, accuracy, and other model-specific issues effectively using issue tracking tools (e.g., Jira).
• Familiarity with methods and strategies to test accuracy in language models, particularly in high-stakes or mission-critical applications like chatbots and film classification.

Preferred Skills & Qualifications

Development Preferences:

• Experience working with Large Language Models or other AI technologies in production web applications.
• Hands-on experience with agentic AI frameworks (e.g., LangGraph, AutoGen, CrewAI, or GCP's Agentic framework).
• Knowledge of agent design patterns, including ReAct (Reasoning and Acting), chain-of-thought prompting, and multi-agent collaboration architectures.
• Experience implementing tool-calling and function-calling capabilities for LLM-powered agents.
• Knowledge of containerisation technologies (e.g., Docker) and orchestration tools (e.g., Kubernetes).
• Understanding of AI model deployment and serving techniques in production cloud environments.
• Familiarity with UX/UI design principles, particularly for AI-driven interfaces like chatbots and agentic AI systems.
• Knowledge of prompt engineering techniques and strategies for optimising agent performance and reliability.
• Experience with multi-cloud architecture patterns and cloud cost optimisation strategies.
• Familiarity with serverless computing and event-driven architectures across AWS, GCP, and Azure.

Testing & Quality Assurance Preferences:

• Experience in conversational AI testing, particularly testing chatbots or conversational agents powered by LLMs like GPT or similar models.
• Knowledge of model evaluation metrics for language models, such as BLEU, ROUGE, and perplexity, and understanding their relevance to accuracy and hallucination testing.
• Familiarity with model fine-tuning and experience testing LLMs after fine-tuning or retraining, ensuring improvements are implemented without introducing new inaccuracies or hallucinations.
• Experience with LLM-specific test documentation, including test plans, test cases, test logs, and issue reports focused on concerns like hallucinations and inaccuracies.