Amicus Therapeutics - Boston, MA
posted 3 months ago
Amicus is an AI startup dedicated to revolutionizing the professional services industry. Our mission is to automate mundane and repetitive tasks in legal firms, consulting firms, and similar sectors, freeing up professionals to focus on higher-value activities. Our innovative approach leverages the latest in AI technology to create solutions that are fundamentally transformative. As an early member of our engineering team, you will play a pivotal role in shaping the direction of our product and technology. We are seeking exceptional candidates who are driven by challenges, thrive on hard work, and have a deep technical expertise that can contribute to the high-velocity growth of our startup. This role is perfect for someone who is gritty, self-directed, and passionate about creating impactful technological solutions in a fast-paced environment. We are in search of a visionary Staff Machine Learning Engineer to spearhead the enhancement of our retrieval models, which are integral to our retrieval-augmented generation (RAG) process. This role will focus on tailoring our retrieval systems to effectively select pertinent documents that serve as the knowledge foundation for subsequent generative tasks. You will lead the development of top-tier retrieval models optimized for the RAG process, ensuring the delivery of highly relevant source material for generative models. You will enhance our RAG framework to improve document encoding, scoring, and selection mechanisms, with an emphasis on natural language understanding. Additionally, you will undertake rigorous experimentation and analysis to benchmark retrieval models against industry standards, focusing on both precision and adaptability for generative tasks. Collaboration with product teams will be essential to ensure seamless integration and alignment of retrieval and generative components. You will drive innovation by staying abreast of emerging trends and methodologies in retrieval systems and their applications within RAG frameworks, and create pipelines to process and analyze documents on a large scale to provide insights for customers.