Data Scientist – LLM & Prompt Engineering

About the role

We are seeking a Data Scientist to join a project focused on leveraging large language models (LLMs) for data processing and insight extraction. The ideal candidate will combine strong data‑science fundamentals with hands‑on prompt engineering and experience in agentic AI frameworks.

Key responsibilities

• Design and implement solutions that use LLMs to process, analyze, and extract insights from both structured and unstructured data.
• Develop and refine prompt engineering strategies to improve accuracy, consistency, and reliability of LLM outputs.
• Build AI‑driven workflows with agentic AI frameworks to automate data‑processing and reasoning tasks.
• Evaluate and experiment with various LLM models, embeddings, and retrieval techniques to identify optimal approaches for use cases.
• Ensure data quality, scalability, and performance of AI‑based processing pipelines.

Required profile

• Strong understanding of LLM‑based data processing and prompt engineering.
• Experience with agentic AI frameworks or similar orchestration tools.
• Proven ability to work with large datasets and develop production‑grade AI pipelines.

Required skills

• Python programming for data processing and AI development.
• Experience with LLM APIs (e.g., Azure OpenAI, Llama).
• Prompt engineering, prompt tuning, and LLM output evaluation.
• Retrieval‑Augmented Generation (RAG) architectures and vector databases such as FAISS, Pinecone, Azure AI Search.
• Agentic AI frameworks (e.g., Semantic Kernel) or similar orchestration platforms.
• Data preprocessing, NLP techniques, and handling large datasets.
• REST APIs, data pipelines, and integration of AI models into enterprise applications.
• Model evaluation, monitoring, and optimization techniques.