✨ About The Role
- The primary responsibility is to develop a high-quality, low-latency retrieval augmented generation (RAG) system.
- The role involves leading the implementation of custom embeddings and rankers to enhance search capabilities.
- The candidate will work with millions of complex financial documents, requiring strong analytical skills.
- Collaboration with a small, dedicated team is emphasized, promoting a culture of rapid iteration and customer feedback.
- The position is based in San Francisco, requiring in-person attendance at the office.
⚡ Requirements
- The ideal candidate will have a strong background in machine learning, particularly in embeddings, ranking, and recommendations.
- A minimum of 3 years of experience in a relevant field is required, showcasing a proven track record in developing machine learning models.
- Proficiency in Python is essential, along with familiarity with large language models (LLMs).
- Experience with Spark and Databricks will be considered a plus, indicating a well-rounded skill set in data processing.
- The candidate should be comfortable working in a fast-paced environment with a focus on delivering high-quality results.