LLM / Prompt Engineer

About the Role

The primary goal of this role is to leverage Large Language Models (LLMs) to develop innovative AI solutions that solve real business challenges. You’ll focus on fine-tuning models, optimizing prompts, and integrating LLM-based systems like RAG into enterprise applications.

Main Responsibilities

• Design, test, and optimize prompts for diverse use cases (e.g., document generation, summarization, information extraction).
• Fine-tune pre-trained LLMs using domain-specific data to improve contextual accuracy.
• Develop solutions using Retrieval-Augmented Generation (RAG) integrated with Vector Databases.
• Guarantee compliance with ethical AI principles (fairness, transparency, accountability).
• Collaborate with business stakeholders to ensure solutions align with goals.
• Contribute to the development of NLP, ML, and AI components.
• Work in Python, use SQL, GitHub, and CI/CD pipelines.
• Deploy and manage solutions on Azure or GCP (depending on the candidate’s stronger side).
• Present technical insights to both technical and non-technical audiences.

Tech Stack & Environment

• LLMs + RAG + Vector DBs
• Languages: Python, SQL
• Tools: GitHub, CI/CD
• Cloud: Azure and/or GCP
• Framework: Not strictly defined yet – the selected candidate will help shape it.

Use Cases

• Prompt engineering for document summarization, content generation, and information extraction.
• RAG-based applications, such as chatbots, use internal company documentation.

Key Requirements (5+ years of experience):

• Deep understanding of LLM architectures and experience with fine-tuning.
• Strong knowledge of RAG, prompt engineering, and vector databases.
• Solid background in NLP, ML, and AI development.
• Experience with Python and SQL; CI/CD practices.
• Proficiency with Azure or GCP.
• Strong communication skills in English, including the ability to present complex topics.

Recruitment Process

• 2-stage process: technical + soft skills.