Software Developer – AI (3+ Years Experience)

Role Overview

This role sits within the Software Development team and is part of Service Delivery, which provides support, consultative services, software development, software testing, customised platform solutions, regulatory compliance, system integrations, data migration, and implementations.

We are looking for a skilled and forward-thinking AI Developer (Generative AI Integration) to lead the development of Generative AI–driven features within our existing web application.

The role focuses on enabling users to input natural language prompts and receive intelligent outputs such as:

• Automated reports and summaries

• Graphical data visualizations

• System-triggered actions (e.g., email dispatch, internal workflows)

All AI-driven functionality must be secure, role-based, and compliant, leveraging AWS Bedrock to translate prompts into safe, structured, and context-aware outputs.

This role will also involve working with machine learning models, vector databases/search, and agentic AI approaches to enhance automation, insights, and overall product capability.

Reporting To

Development Team Lead / Head of Software Engineering

Key Responsibilities

AI Solution Development

• Collaborate with stakeholders to gather and refine requirements for AI-driven solutions

• Design and implement a natural language prompt interface within the web application

• Integrate Claude 3 / 3.5 Sonnet or other LLMs via AWS Bedrock for secure and contextual prompt processing

• Transform AI outputs into:

  • Structured reports (summaries, insights)

  • Charts and graphs generated from internal datasets

  • System actions such as email notifications or internal workflow triggers

• Implement AI workflows with strict role-based access control (RBAC)

• Design logic to interpret, validate, and safely execute AI-generated outputs

• Collaborate closely with frontend and backend developers to ensure seamless UI/UX integration

• Optimize prompt engineering, token usage, and response reliability

• Monitor, log, and analyze LLM interactions, including graceful fallback handling

• Work closely with the Development Team Lead and Head of Software Engineering to embed AI modules into the product

• Perform functional and regression testing for AI features across real-world use cases

• Partner with QA teams to define and implement AI testing frameworks

Security & Compliance Awareness

This role involves working with role-restricted and sensitive data. Candidates must demonstrate awareness of:

• Data privacy and protection best practices

• Secure coding standards

• Controlled execution and validation of AI-generated actions

Required Qualifications & Skills

Essential Skills

• Bachelor’s or Master’s degree in Computer Science, AI, Data Science, or a related field

• 3+ years of software development experience, with at least 1 year in AI/LLM integration

• Proficiency in Python, C#, or JavaScript/TypeScript (depending on the tech stack)

• Hands-on experience with AWS Bedrock, especially Claude 3 / 3.5 Sonnet, or other LLM platforms (OpenAI, Anthropic, Cohere, etc.)

• Strong understanding of prompt engineering, context management, and output parsing

• Experience implementing role-based access control (RBAC) in AI workflows

• Experience working with REST APIs, microservices, and cloud-based applications

• Ability to process structured and unstructured data and generate dynamic visualizations (Chart.js, Plotly, or similar)

• Strong debugging, testing, and validation skills, particularly for AI-driven system actions

• Experience with cloud-based AI tools and environments

• Strong communication skills to explain technical concepts to both technical and non-technical stakeholders

Nice-to-Have Skills

• Experience with LangChain, agent frameworks, or LLM tool-calling approaches

• Exposure to MLOps, AI monitoring, or production model lifecycle management

• Experience working on multi-tenant, enterprise, or compliance-sensitive systems

• Understanding of data governance, ethical AI, and responsible AI practices

Key Performance Indicators (KPIs)

• Accurate task estimation versus actual delivery time

• Minimal rework required after task completion

• Consistent delivery within agreed timelines

• Quarterly AI model monitoring and retraining, with documented performance metrics and corrective actions

• Complete, clear, and timely documentation for all AI-related projects