Applied AI Engineer - AI Labs

AI Labs is responsible for building and deploying next-generation AI-powered solutions across the organisation and for our clients. Our focus is on creating production-grade systems using Large Language Models (LLMs), intelligent agents, and retrieval-based architectures that automate workflows, enhance decision-making, and accelerate delivery across the enterprise. This role is hands-on and delivery-focused. The Applied AI Engineer will work on building, integrating, and scaling real-world AI systems rather than on model research or algorithm development.

Responsibilities:

• Design, develop, and deploy AI-driven solutions using Large Language Models (LLMs) and related technologies.
• Build and maintain Retrieval-Augmented Generation (RAG) pipelines, agent-based workflows, and AI orchestration layers.
• Integrate LLM-powered capabilities into enterprise applications, internal tools, and client-facing platforms.
• Develop prompt frameworks, tool-calling logic, and guardrails to ensure reliable, safe, and high-quality AI outputs.
• Implement evaluation, monitoring, and feedback mechanisms to continuously improve accuracy, cost efficiency, and system performance.
• Work closely with business stakeholders, product teams, and engineering teams to translate requirements into scalable AI solutions.
• Document architectures, workflows, and implementation patterns to support maintainability and knowledge sharing.

Requirements:

• Strong proficiency in Python and experience building API-driven applications.
• Hands-on experience working with Large Language Model platforms (e. g., OpenAI, Anthropic, Groq, or similar).
• Experience with prompt engineering, structured outputs (JSON, tool calling), and multi-step LLM workflows.
• Experience with vector databases and embedding-based retrieval systems (e. g., FAISS, Pinecone, Weaviate, Chroma).
• Familiarity with integrating AI systems with databases, APIs, and enterprise software.
• Experience building or working with RAG pipelines, intelligent agents, or multi-model orchestration frameworks.
• Understanding of performance, cost, and reliability trade-offs in production AI systems.
• Familiarity with frameworks such as LangChain, LangGraph, CrewAI, or similar is a plus.
• Experience deploying or operating AI-powered services on cloud platforms such as AWS, Azure, or GCP.
• Familiarity with monitoring, logging, and maintaining production services is desirable.
• Strong problem-solving and analytical skills with the ability to work on ambiguous, evolving AI use cases.
• Ability to collaborate with cross-functional teams and communicate complex technical concepts clearly.
• A proactive mindset with a strong interest in emerging AI technologies and applied innovation.
• Comfortable working in a fast-paced, experimental environment where rapid iteration is expected.
• 1-4 years of experience in software engineering, data engineering, or applied AI development.
• Bachelor's or Master's degree in Computer Science, Engineering, or a related field (or equivalent practical experience).