Machine Learning Engineer

AboutFintool is a financial copilot for institutional investors. It’s ChatGPT on top of financial documents, starting with SEC filings. Fintool is engineered to discover financial insights beyond the reach of timely human analysis or search software.Fintool is backed by Y Combinator and entrepreneurs such as the co-founders of Datadog, Vercel, HuggingFace, or domain experts from OpenAI to Deepmind.TeamNicolas Bustamante (CEO): spent 7 years building one of the largest AI-driven legal search engines (Bloomberg for lawyers). Nicolas hired nearly 200 people, secured millions of dollars in debt and equity funding, and the profitable business was successfully acquired by Summit Partners, a $43B billion growth equity fund, for $x00M+.Edouard Godrey (CTO): worked for nine years at Apple, leading teams of data scientists and engineers. He worked on Apple Search (Spotlight) and Apple Pay, maintaining big data pipelines and deploying cutting-edge AI models. He received the 2019 Apple Pay Innovation Award for outstanding contributions and fresh insights.Matt DePero (Data Engineer): worked at Google and then at the search engine Neeva (acq. by Snowflake) where he built the crawl-to-index pipeline infra processing petabytes of data.Working philosophySmall team : small in-person teams outperform large and well-funded companies. When people visit our office, they should be surprised by how few people we are.Ship code : we avoid meetings, PM jargon to release early, release often, and listen to customers.In-person : we believe high-performing teams do their best work, build long-term relationships, and have the most fun in person.Company ValuesClone and improve the best : we're not about reinventing the wheel but about enhancing proven success. We are shameless cloners who stand on the shoulders of giants. We draw inspiration and then create differentiation because distinctiveness drives dominance.Release early, release often, and listen to your customers : speed matters in business, so we push better-than-perfect updates for customers asap. Mastery comes from repeated experiments and learning from mistakes rather than putting in a set number of hours. It’s 10,000 iterations, not 10,000 hours.Warren Buffett : We model our personal and professional ethos on the principles he exemplifies. Upholding integrity, valuing honesty, practicing frugality, championing lifelong learning, embracing humility, extending generosity, applying rationality, and demonstrating patience. Every day, we strive to mirror these Buffett-inspired virtues.Job DescriptionYour challenge is to develop a high-quality, low-latency retrieval augmented generation (RAG) on top of millions of complex documents. You will lead the implementation of custom embeddings, rankers, and hybrid search.Requirements:PythonMachine Learning (embeddings, ranking, recommendations)LLMKnowledge of Spark, Databricks, and Typescript is a plus.Experience:

3+ yearsLocation:

San Francisco (no remote)Contract:

Full-timeApply via the form below:

Application Link

#J-18808-Ljbffr