Data Scientist / Unstructured Data

Intersog® is a leading provider of custom web and mobile development solutions, serving Fortune 500 companies, SMEs, and startups. Our goal is to exceed client expectations by delivering end-to-end solutions and project resources that drive innovation, industry leadership, and business strategy.

Summary:

We are seeking for a talented Data Scientist to join our team and play a key role in unlocking insights from massive amounts of unstructured data. You will leverage your expertise in Natural Language Processing (NLP) and advanced techniques like Large Language Models (LLMs) to generate analyst-style reports and build innovative solutions on the Microsoft Azure platform.

Responsibilities:

• Design and implement strategies to extract meaningful insights from large, unstructured datasets.
• Develop and train custom Machine Learning models for specific NLP tasks.
• Utilize Microsoft Azure tools like Form Recognizer, Azure Cognitive Search (Indexer, Skillset, and Indexes) to streamline data processing and retrieval.
• Work with Large Language Models (LLMs) to generate reports and enhance data analysis.
• Apply Retrieval-Augmented Generation (RAG) strategies and prompt engineering techniques to optimize LLM performance.
• Leverage LangChain libraries for splitting, vectorizing, and integrating different LLMs within the Azure environment.

Requirements

• Bachelor's degree in Computer Science, Data Science, or a related field.

• Proven experience working with large, unstructured datasets.
• Strong understanding of NLP fundamentals, including text processing, machine learning algorithms, and deep learning techniques.
• Experience training and deploying Machine Learning models for NLP tasks.
• Experience working with Large Language Models (LLMs) like GPT-4
• Familiarity with Retrieval-Augmented Generation (RAG) strategies and prompt engineering best practices.
• Hands-on experience with LangChain libraries for data manipulation and LLM integration within the Azure environment.
• Proficiency in Python.
• Working knowledge of the Microsoft Azure cloud platform and its AI services (Azure Cognitive Search, LLMs, etc.) is a strong plus.
• Excellent communication, collaboration, and problem-solving skills.