Applied AI Engineer (LLM/AI Agents)

Role Synopsis:

The Applied AI Engineer will be responsible for designing and delivering practical AI-powered solutions that enhance core business operations, mainly across construction, procurement, and legal functions. This role focuses on building and deploying AI assistants (“agents”) using large language models (LLMs) to process and extract insights from unstructured data such as contracts, tenders, BOQs, and reports.

Working at the intersection of business and technology, the engineer will develop end-to-end AI applications, including document analysis tools, knowledge retrieval systems, and decision-support assistants. The role requires a strong hands-on approach, rapid prototyping, and the ability to work effectively with fragmented and real-world data environments.

Key Accountabilities:

• Design, develop, and deploy AI-powered assistants (“agents”) to support business functions such as legal, procurement, and construction
• Build and maintain LLM-based applications using external APIs (e.g., OpenAI, Anthropic), ensuring scalability and reliability
• Develop and optimize Retrieval-Augmented Generation (RAG) pipelines for accurate and context-aware document analysis
• Process, structure, and extract insights from unstructured data sources, including contracts, PDFs, Excel files, and emails
• Collaborate with business stakeholders to identify high-impact use cases and translate them into practical AI solutions
• Rapidly prototype and iterate AI tools, delivering working solutions within short development cycles
• Continuously improve AI output quality by reducing hallucinations and enhancing accuracy and consistency
• Integrate AI solutions with internal data pipelines and systems in collaboration with data engineering teams
• Ensure proper documentation, maintainability, and scalability of developed AI applications
• Monitor performance and usage of AI tools, incorporating user feedback to drive improvements and adoption
• Stay up to date with advancements in LLMs and AI tools, and apply relevant innovations to business use cases
• Contribute to establishing best practices, standards, and governance for AI development within the organization

Desired background:

• Bachelor’s or Master’s degree in Computer Science, Engineering, Data Science, or a related field
• 2–5 years of experience in software engineering, AI/ML engineering, or applied AI roles
• Proven experience building and deploying real-world AI/LLM applications (beyond academic or tutorial projects)
• Hands-on experience working with large language models (LLMs) and related frameworks (e.g., LangChain, LlamaIndex, or similar)
• Experience working with unstructured and semi-structured data (documents, PDFs, Excel files, emails)
• Strong experience in developing end-to-end solutions, from data processing to application delivery
• Experience integrating APIs and working with external services
• Familiarity with data pipelines and collaboration with data engineering teams
• Exposure to cloud environments (AWS, Azure, or GCP) and modern development practices
• Experience working in fast-paced, delivery-oriented environments with a focus on practical outcomes
• Demonstrated ability to work on ambiguous problems and translate business needs into technical solutions

Required skills:

• Strong programming skills in Python, with ability to write clean, maintainable, and production-ready code
• Hands-on experience with large language model (LLM) APIs (e.g., OpenAI, Anthropic) and building LLM-based applications
• Solid understanding and practical application of:
• Prompt engineering
• Retrieval-Augmented Generation (RAG)
• Context management and prompt optimization
• Experience working with unstructured and semi-structured data (PDFs, documents, Excel, emails)
• Familiarity with AI/LLM frameworks such as LangChain, LlamaIndex, or similar
• Experience integrating APIs and working with external services
• Ability to design and build end-to-end AI solutions (data ingestion → processing → model → output)
• Understanding of common LLM challenges (e.g., hallucinations, context limitations) and techniques to mitigate them
• Basic knowledge of data pipelines and collaboration with data engineering workflows
• Strong problem-solving skills and ability to work in ambiguous, real-world environments
• Ability to communicate technical concepts clearly to non-technical stakeholders