Data Scientist LLM (m/f/d)

Michael Bailey Associates AG; Singapore; On-site; SGD 100,000 - 125,000; Full time

Job summary

A leading company in Singapore is seeking a Data Scientist to develop an AI-powered application focusing on the analysis and compliance of corporate reports. The role involves building a text processing module and an efficient information retrieval system, emphasizing quantitative text analysis and Python programming skills. The ideal candidate will collaborate closely with clients, utilizing their expertise to deliver a comprehensive tool for regulatory compliance.

Qualifications

• Experience in quantitative text analysis required.
• Proficiency in Python programming and relevant NLP libraries.
• Experience in deploying Python code in MS Azure or Snowflake.

Responsibilities

• Develop AI application for compliance analysis of corporate reports.
• Implement search indexing and retrieval systems.
• Classify text segments according to regulatory frameworks.

Skills

Quantitative text analysis

Python programming

NLP libraries (spaCy, NLTK, sbert)

English proficiency

Tools

NLP libraries (spaCy, NLTK, sbert)

Microsoft Azure

Job description

We are currently looking for a Data Scientist(m/f/d) -AI LLM

Project description: To develop an AI-powered application that automates the analysis, classification, and semantic processing of annual combined corporate reports, with a focus on compliance with regulatory standards such as IFRS and ESRS.

Task (performed independently):

? Building of a scraping and text preparation module for extracting content from combined reports by taking into consideration information and requirements provided by the client in advance based on own knowledge and experience
? Implementation of a search indexing and retrieval system for efficient information access
? Classification of text segments according to regulatory frameworks (IFRS, ESRS)
? Development of a matching engine to link regulatory descriptions to actual document content
? Development of a text consistency checking algorithm
? Integration of Named Entity Recognition (NER) with a labeling interface for additions
? Analysis of evaluation methods for the rewriting and rewording capabilities of large language models (LLMs) for editing the documents
? Creation of a user-facing interface for the above tasks
? Documentation of the results and presentation (online meeting) to client for a sign-off and handover
? Technical consultation of end users with respect to the developed tool and methods based on own expertise

Client provides all necessary information, access to the systems and requirements in advance.

Skills:
Must haves:
• Experience in quantitative text analysis
• Proficiency in Python programming and relevant NLP libraries (e.g., spaCy, NLTK, sbert)
• Experience in developing and deploying Python code in MS Azure or Snowflake environment
• English (spoken and written).

Nice haves:
• Experience in programming with LLM inference APIs
• Background in software development or corporate finance
• Knowledge of Microsoft Azure services (AI Foundry, AI Search, Batch, Blob storage, Function, ML Service, Key Vaults, etc.); Knowledge of Microsoft Office backends such as SharePoint and Outlook APIs
• Proficiency in German.

We are looking forward to hearing from you. Please apply with your most recent CV