Core Engineering, Knowledge Graph Software Engineer, Associate/ Vice President, Singapore

DEVELOPER JOURNEY STRATEGY AT GOLDMAN SACHS

The Developer Journey Strategy focuses on investing in the developer experience to minimize friction, promote standardization, and leverage artificial intelligence (AI) to enable seamless delivery. By streamlining processes, implementing consistent practices, and integrating AI-driven tools and solutions, we empower developers to efficiently build and run products and platforms. This strategy aims to enhance productivity, foster innovation, and ensure high-quality outcomes by providing developers with the advanced tools, resources, and support they need to succeed. The incorporation of AI not only automates routine tasks and optimizes workflows but also provides predictive insights and intelligent recommendations, further enhancing the development process.

SDLC ENGINEERING

Part of the Goldman Sachs’ Core Engineering group's function is to provide best in class language support and tooling for our engineering community to facilitate the building, testing and deployment of their products. We strive for our tooling to improve product quality, developer productivity and increase opportunities for collaboration. Our aim is to innovate and drive technology solutions that will impact the bottom line for the firm. By joining us, you will be part of a diverse global technical team focusing on solving critical business problems. You will be working at the heart of the developer experience, ensuring the code that is written by thousands of GS engineers is versioned securely, reviewed expertly, compiled quickly, tested comprehensively, and distributed widely. 

WHAT YOU WILL BE WORKING ON

The Knowledge Engineering team builds platforms to access, understand, and leverage institutional knowledge effectively. Our mission is to transform how information is managed and retrieved across the firm, driving innovation and productivity through data and AI solutions. We are seeking a highly skilled and motivated Engineer to join our Knowledge Engineering team. This critical role will focus on designing, building, and maintaining our internal knowledge graph, a foundational component for AI-driven capabilities. Leveraging Large Language Models (LLMs) and vendor products, you will be instrumental in creating a unified, intelligent system that democratizes access to complex organizational data, enhances decision-making, and supports the firm's strategic initiatives.

Responsibilities:

• Design, develop and maintain robust data retrieval systems to supply our Generative AI infrastructure with the organizational and systems knowledge they need from vast unstructured data corpuses.
• Lead the modeling and evolution of the knowledge graph, ensuring efficient, scalable, and accurate representation of complex unstructured information across the organization.
• Ensure conformance with the firms security and AI standards.
• Integrate our generative AI systems with the knowledge graph to enhance AI-driven reasoning, semantic search, and contextual data retrieval, ensuring accuracy and reducing hallucinations.
• Work extensively with the vendor products, configuring integrations with various internal data sources and leveraging capabilities to build a unified and intelligent enterprise data retrieval.
• Collaborate closely with product managers, AI/ML engineers, and other stakeholders to understand data requirements, define KPIs, and deliver data solutions that align with business objectives.
• Ensure data quality, integrity, and security within the knowledge graph, implementing robust validation and monitoring mechanisms.
• Contribute to the continuous improvement of data engineering best practices, tools, and processes within the SDLC Engineering team.

Basic Qualifications:

• Bachelor's or Master's degree in Computer Science, Data Engineering, or a related technical field.
• Minimum 5 (for associate)/ 10 (for vice president) years of hands-on experience in data engineering, with a strong focus on building scalable distributed systems.
• Proficiency in programming languages such as Python or Java.
• In depth knowledge of modern network stacks, ideally with http proxies / gateways / load-balancing.
• Experience with cloud platforms (e.g., AWS, GCP, Azure).
• Solid understanding of data structures, algorithms.
• Familiarity with SDLC processes and tools.

Preferred Experience:

• Familiarity with Large Language Models (LLMs) and their application in enterprise search or knowledge management.
• Familiarity with LLM communication protocols (MCP, A2A etc).
• Direct experience with enterprise AI search platforms that leverage knowledge graphs.
• Proven track record in designing and implementing production-grade knowledge graphs.
• Experience with Retrieval Augmented Generation (RAG) methodologies and prompt engineering for LLMs.
• Experience with data governance, metadata management, and data cataloging.