AI / ML Full Stack Engineer

Responsibilities:

• Design, develop, and deploy AI-powered applications leveraging Large Language Models (LLMs) such as GPT, Claude, Gemini, and LLaMA.
• Create, optimise, test, and evaluate prompts to improve model performance, accuracy, and user experience.
• Develop and maintain full-stack applications using Python for backend services and React.js for frontend development.
• Integrate AI models and APIs into business applications and workflows.
• Build scalable cloud-native solutions on AWS or GCP.
• Analyse AI-generated outputs and continuously refine prompts, workflows, and system behaviour.
• Implement best practices for model orchestration, prompt management, and LLM evaluation.
• Collaborate with product, engineering, and business teams to translate requirements into AI-driven solutions.
• Participate in rapid prototyping, experimentation, and deployment of new AI use cases.
• Ensure application reliability, performance, security, and scalability.