Ai Engineer, Vp - Natural Language Processing (New York, Ny)

How will you fulfill your potential?
A true greenfield opportunity, you will join the team as we embark on creating new, scalable and resilient Generative AI platform leveraging large language models for a complex finance industry. You will collaborate with other NLP engineers, data scientists and business leaders to understand challenges facing the firm and its clients. Your design and development work will contribute to a world-class client experience and optimize business performance.
Your Impact
You will be joining the team that builds and operates foundational Generative AI platform, used by the rest of Goldman Sachs to apply Conversation AI and Document AI based digitization, automation, productivity improvement and efficiency gains to the daily operations of the firm. We take the best components from open source and major cloud providers and adapt and expand them to accommodate unique needs of the firm.
Our Impact
At Goldman Sachs, our Engineers don’t just make things – we make things possible. Change the world by connecting people and capital with ideas. Solve the most challenging and pressing engineering problems for our clients. Join our engineering teams that build massively scalable software and systems, architect low latency infrastructure solutions, proactively guard against cyber threats, and leverage machine learning and natural language modeling alongside financial engineering to continuously turn data into action. Create new businesses, transform finance, and explore a world of opportunity at the speed of markets. Engineering is at the critical center of our businesses. Our dynamic environment requires strategic thinking that is innovative and produces smart solutions.
The Goldman Sachs NLP and AI Platform team provides high-impact solutions for our engineers and business users responsible for solving problems of significant business value across multiple divisions of the firm. We build scalable and resilient systems using predictive modeling, natural language processing, deep learning, and other techniques on high-volume and high-velocity data.
Responsibilities May Include

• Collaborating with cross-functional teams to integrate NLP solutions into existing applications and systems.
• Build conversational AI services using Large Language Models that can enable interactions such as question and answering, summarization.
• Optimize, Fine tune and implement deep learning models on information extraction tasks like NER, Summarization and Question Answering.
• Build and enhance orchestration tools to enable semantic search data ingestion pipelines that will be used in document ingestion, vector embedding for document digitization, search and retrieval and conversational services.
• Experiment & select appropriate AI models for a use case as well as building and training working versions of the models using AI platform.
• Evaluating the performance of NLP models and refining them to improve accuracy and efficiency.
• Create reusable patterns, libraries and datasets.
• Developing and implementing techniques for improving search and retrieval algorithm using language models.
• Conducting research to identify new NLP techniques and approaches,

Qualifications And Desired Skillsets Include

• Excellent communication and collaboration skills, as well as the ability to work independently and manage multiple projects simultaneously.
• 1+ year of experience in building platforms using document extraction using Apache Nutch, JSoup etc.
• 1+ year of experience with data pipeline orchestration tools as such Flyte, Airflow, Metaflow, experience with Big Data tools such as PySpark, Kafka.
• 1+ year of experience in building Conversational AI services and orchestration using tools such as LangChain, Vector DB, LLMs, Inference tools such as AWS Sagemaker and experience in Prompt Engineering.
• Working experience with deep learning frameworks such as TensorFlow and PyTorch.
• Knowledge of natural language understanding, question answering, summarization, sentiment analysis, and other NLP tasks.
• A degree in computer science, computational linguistics, or a related field.
• Experience in designing and implenting large information retrieval systems using embeddings (ex: MiniLM), vector stores like (Faiss, PineCone, Vespa), similarity match & ranking techniques.
• 3+ years of Python and/or Java programming experience.

About Goldman Sachs
At Goldman Sachs, we commit our people, capital and ideas to help our clients, shareholders and the communities we serve to grow. Founded in 1869, we are a leading global investment banking, securities and investment management firm. Headquartered in New York, we maintain offices around the world.
We believe who you are makes you better at what you do. We're committed to fostering and advancing diversity and inclusion in our own workplace and beyond by ensuring every individual within our firm has a number of opportunities to grow professionally and personally, from our training and development opportunities and firmwide networks to benefits, wellness and personal finance offerings and mindfulness programs. Learn more about our culture, benefits, and people at GS.com/careers.
We’re committed to finding reasonable accommodations for candidates with special needs or disabilities during our recruiting process. Learn more: https://www.goldmansachs.com/careers/footer/disability-statement.html
© The Goldman Sachs Group, Inc., 2023. All rights reserved.
Goldman Sachs is an equal employment/affirmative action employer Female/Minority/Disability/Veteran/Sexual Orientation/Gender Identity