Research Automation System Engineer (Intern)

**Job Title:** Research Automation System Engineer (Intern) **Location:** Hong Kong (On-site) **Duration:** 2-3 months **About Us** We are a Hong Kong-based equity long-only fund managing US$1 billion in AUM. We employ a fundamental, research-driven, bottom-up investment process. To maintain our edge, we are building an internal AI-integrated research system designed to automate workflows, centralize intelligence, and improve research productivity and information processing efficiency. **The Role** We are seeking a highly capable Research Automation System Engineer—ideally an advanced degree candidate in a quantitative field—to work directly alongside our investment team in this internship role. Your mandate is to architect the data orchestration and intelligence layer of our research system. Your value add will be in workflow automation, data extraction, and AI engineering—turning unstructured data from fragmented financial sources into structured, searchable institutional knowledge. A monthly stipend is provided to support living expenses during the internship. **Core Responsibilities** 1. Design and maintain automated pipelines to capture and centralize information from diverse sources; 2. Direct the automated conversion of all incoming data into standardized, high-quality OCR PDF formats; 3. Architect and maintain a programmatic folder system that routes files accurately into specific industry and company repositories; 4. Deploy Large Language Models (LLMs) to automatically generate structured insights, core takeaways, and briefs from newly ingested company data; 5. Build monitoring tools to track specific business drivers and configure an internal alerting system that notifies the investment team when material information changes. 6. Implement a Retrieval-Augmented Generation (RAG) conversational chatbot, allowing the investment team to interactively query and cross-reference the document repository. 7. Engineer the alert and chat interfaces so that every insight or notification links directly back to both its source OCR PDF file and its corresponding AI summary page in a single click. **Requirements** * Currently pursuing an advanced degree in Computer Science, Data Science, Engineering, or a highly quantitative field. * Strong Python development skills, with hands-on experience handling web scraping, API integrations, and automation hooks. * Strong SQL skills and familiarity with document processing tools (e.g., OCR libraries, PDF parsers). Experience dealing with metadata tagging and source citation mapping is highly valued. * Strong hands-on experience deploying and running open-source tools locally, managing local databases and setting up local system environments on standalone hardware. * Experience applying LLM APIs, advanced prompt engineering, and Vector Databases / RAG frameworks to build conversational chatbot interfaces with accurate source citation mechanisms. * Strong interest in public equity markets and fundamental investment research. Qualified candidates will be notified via email on next step. Thank you for your interest.