Foundation Engineering - AI Platform, GenAI Search and Document Management Developer

Goldman Sachs has a unique and differentiated set of data, including proprietary content, analytics, and research; leveraging these unique datasets and content will enable the firm to double down on its existing strengths and harness the power of Generative AI.
We are seeking for highly motivated Engineers to join our Search and DocAI organization. 

The platform you will build acts as a central knowledge layer for the firm’s data which serves relevant search results to a diverse set of agentic systems and tools. You will be building a low latency distributed system that powers the Search system along with building capabilities that enhances search efficiency and accuracy of agentic use cases across the firm. You will play a pivotal role in driving the adoption of cutting-edge Generative AI technologies at the firm interacting directly with our business.
In this role, you will have the opportunity to contribute to various Generative AI domains, including boosting developer productivity with Retrieval-Augmented Generation (RAG) pipelines and knowledge graphs for information retrieval. 
You will help address the unique challenges that arise in generative AI systems within the financial domain and contribute to the development of Goldman’s AI Assistant to empower our business. 

What you will do

• Collaborating effectively with colleagues to build an AI enabled platform for Document Digitization and Search.
• Conceptualizing, experimenting with, and assessing AI-based software systems.
• Developing, testing, and maintaining high-quality, scalable. production-ready code.
• Demonstrating technical leadership by taking charge of cross-team projects.
• Developing and deploying services in cloud native environment.
• Contributing to boost developer productivity with Generative AI. 

Required Qualifications

• Min. 3 years' experience as a backend Java developer with experience writing multi-threaded, concurrent, scalable, and distributed applications
• Must be up to date on current and opensource stack (e.g. Kafka, ElasticSearch, gRPC, MongoDb etc.)
• Experience with writing microservices and distributed applications
• Knowledge of Python especially in the NLP and data manipulation area
• Knowledge of how search engines work and LUCENE
• Knowledge of vector database is a plus