Role Description We are seeking a visionary and highly skilled Senior Data Scientist to lead the development of a cutting-edge document intelligence and discovery platform. This unique role sits at the intersection of advanced Generative AI, Machine Learning, and Cheminformatics. Your primary mission will be to solve a highly complex unstructured data challenge: transforming scanned PDF documents containing intricate chemical structures into highly searchable, interpretable, and actionable knowledge bases. - Architect Document Intelligence Solutions: Design and implement advanced Machine Learning and Deep Learning models to parse, extract, and interpret text and complex chemical structures from unstructured, scanned PDF documents. - Develop LLM & Retrieval Systems: Build and optimize Large Language Model (LLM) applications, leveraging vector databases to enable semantic search, advanced data interpretation, and retrieval-augmented generation (RAG). - End-to-End ML Pipelines: Own the entire machine learning lifecycle, including data preprocessing (specifically for chemical data and OCR outputs), model training, evaluation, deployment, and post-deployment monitoring. - Bridge Chemistry & AI: Apply your chemistry domain knowledge to translate molecular structures, diagrams, and chemical data into machine-readable formats, embeddings, and actionable insights. - Cloud Architecture & Deployment: Deploy scalable, secure, and production-ready AI/ML pipelines within the AWS ecosystem, ensuring high availability and performance. - Cross-Functional Collaboration: Partner closely with software engineers, data engineers, and domain experts to integrate ML models into the core product architecture and align with business goals. Qualifications - 5+ years of proven experience working as a Data Scientist, with a track record of delivering production-grade machine learning models. - A strong background in Chemistry, Cheminformatics, or a highly related scientific field, with a demonstrated ability to interpret and manipulate complex chemical structures and data types. - Advanced proficiency in Python and deep hands-on experience with the AWS cloud stack (e.g., SageMaker, Lambda, S3, EC2). - Practical, hands-on experience working with LLMs (fine-tuning, prompt engineering, or API integration) and vector databases (e.g., Pinecone, Milvus, Weaviate, or Qdrant). - Robust experience in model development, validation, deployment, and evaluation framework tools (e.g., PyTorch, TensorFlow, Scikit-Learn). - Prior experience with Computer Vision, Optical Character Recognition (OCR), or Document AI systems is highly desirable given the scanned PDF focus. - Strong analytical problem-solving skills, excellent communication, and the ability to thrive in a highly collaborative, cross-disciplinary project environment. Benefits - Ecosystem of Opportunity: You'll be part of a growing network where client engagements, thought leadership, research collaborations, and mentorship paths are interconnected. - Collaborative Environment: Our culture thrives on openness, continuous learning, and engineering excellence. - Flexible & Impact-Driven Work: Whether you're contributing from a client project, innovation sprint, or open-source initiative, we focus on outcomes—not hours. - Talent-Led Innovation: Our Innovation Community isn’t just a knowledge-sharing forum—it’s a launchpad for members to lead new projects, co-develop tools, and shape the direction of AI itself.

• Work with various ERP and IOT data sources to Build interactive and dynamic Power BI dashboards for data storytelling and stakeholder decision support • Design and develop machine learning models and predictive analytics solutions using data sourced from Snowflake • Perform data exploration, statistical analysis, and feature engineering to support AI initiatives • Collaborate with data engineering teams to ensure robust data pipelines • Contribute to the development of AI-driven tools and frameworks within the organization • Evaluate model performance and retrain as needed to adapt to evolving data • Participate in cross-functional projects involving manufacturing, quality, supply chain and engineering. • Update training, and documentation. • Deliver user training to operating groups as required. • Other duties as assigned

• Own marketing analytics across DTC and Amazon, including paid acquisition, retention, LTV, and channel-level performance. • Build and maintain attribution models for DTC acquisition that account for multi-touch and organic effects—not just last-click. • Analyze Amazon performance data including traffic, conversion, ad spend efficiency, and organic/paid contribution. • Identify performance trends and surface actionable insights to growth leads on a regular cadence. • Support the Growth Marketing and Ecommerce teams on the design and analysis of A/B and multivariate tests across paid channels, email, website, and Amazon storefronts. • Set standards for test design, sample sizing, and statistical significance across the marketing team. • Support the ecommerce team on updating Marketing on website and digital storefront performance analysis. • Track and report on conversion funnel metrics, site behavior, and the impact of UX or merchandising changes. • Support the CMO and VP of Growth in the monthly revenue forecasting cycle — pulling and organizing upstream inputs, updating the growth model, and flagging anomalies or trends that warrant a closer look. • Take ownership of running and interpreting incrementality testing tool and use results to inform channel investment decisions.

Title: Data Scientist Location: San Francisco United States Location Type: Hybrid Job Description: About Us: At Parafin, were on a mission to grow small businesses. Small businesses are the backbone of our economy, but traditional banks often dont have their backs. We build tech that makes it simple for small businesses to access the financial tools they need through the platforms they already sell on. We partner with companies like DoorDash, Amazon, Worldpay, and Mindbody to offer fast and flexible funding, spend management, and savings tools to their small business users via a simple integration. Parafin takes on all the complexity of capital markets, underwriting, servicing, compliance, and customer service for our partners. Were a tight-knit team of innovators hailing from Stripe, Square, Plaid, Coinbase, Robinhood, CERN, and more all united by a passion for building tools that help small businesses succeed. Parafin is backed by prominent venture capitalists including GIC, Notable Capital, Redpoint Ventures, Ribbit Capital, and Thrive Capital. Parafin is a Series C company, and we have raised more than $194M in equity and $340M in debt facilities. Join us in creating a future where every small business has the financial tools they need. The Data Science Team Our Impact Data is core to Parafins mission to grow small businesses. Our platform partnerships and portfolio provide rich insight into SMB financial health, allowing us to create fair, automated, and broad access to financial services. As Parafin scales, the breadth and depth of our data grows with it, amplifying the impact we can have on customers and the trajectory of the business. Our Team Enthusiasm, skepticism, and respect for data are in our DNA two of our co-founders were PhD data scientists at Robinhood. Since our founding, we have grown the team to include perspectives from graduate studies in physics, mathematics, bioengineering, economics, financial engineering, and electrical engineering and professional experience at Robinhood, Uber, Lyft, Airbnb, Faire, Segment, Facebook, and Google. We value first-principles thinking, attention to detail, and craftsmanship. Our Work Our mission is to help Parafin succeed by leveraging the vast data that powers our platform. Our team partners closely with leaders across the company to drive impact. This roles scope includes: Growth: We design experiments and analyses that expand access to capital while keeping the portfolio healthy. Example projects: - Designing experiments that navigate the tradeoff between growth and risk expanding access to capital while keeping the portfolio healthy - Studying the full merchant lifecycle first offer, repayment, repeat capital to find where we can responsibly extend more - Modeling how a prospective partners portfolio would perform on our platform, so we can size new opportunities before launching Portfolio Monitoring & Servicing: We build models and tooling that forecast portfolio performance and measure the impact of our servicing efforts on merchant outcomes. Example projects: - Building and shipping ML models (XGBoost and friends) that forecast merchant repayment behavior from feature engineering through production deployment to inform how we price and size offers - Measuring whether our servicing actually works how much balance we recover after reaching out to a struggling merchant, and what interventions move the needle Infrastructure: We build the data pipelines, automated systems, and internal tools that let the rest of the company operate at scale. Example projects: - Building the data pipelines that power every analysis, dashboard, and ML model across the company - Automating processes lien filings, KYC checks, fraud screens using APIs, ML, and LLMs - Building internal tools Streamlit apps, dashboards, Slack bots that the rest of the company uses every day Beyond these focus areas, our team helps expand our impact by recruiting exceptional talent, improving our tools, and supporting each other through regular seminars and project reviews. About You Your Impact You will make an outsized impact on Parafins trajectory by leading projects from end to end. You will quickly learn new methods, apply them across diverse areas of the business, and implement them robustly. You will develop expertise in specific areas of the business, but may tackle projects across domains as our priorities evolve. Your Background and Skills Bachelors Degree (or higher) in Computer Science, Statistics, Mathematics, Data Science (or related fields). We believe the most effective data scientists bring the following skills to their work: - Statistical Reasoning - Approach data analysis with a critical, intellectually honest eye - Design concise metrics that guide decision making - Use robust causal inference methods - Develop valid and predictive machine learning models - Business Acumen - Identify and effectively prioritize business problems - Solve business problems using appropriate data science techniques - Anticipate the impact of your work on our financial performance, customers, and compliance obligations - Engineering Mindset - Write legible, reliable, and tested code - Build or source tools to boost the teams efficiency - Contribute to model and data infrastructure design - Leadership and Collaboration - Model Parafins values of efficiency, intellectual honesty, accountability, and empathy - Build trusted relationships with stakeholders - Document work, seek feedback, and share learnings proactively - Mentor other DS members on the team - Management experience, a plus! - Focused Execution - Prioritize high-impact use of your time - Scope projects rigorously - Act with urgency - AI Tool Fluency - Rapidly learn and adopt emerging AI tools and workflows to accelerate analysis - Critically evaluate AI-generated outputs for accuracy and reliability What We Offer - Salary: $200k - $235k Senior/Staff Level: $235k - $330k+ - Equity grant - Medical, dental & vision insurance - Work from home flexibility - Unlimited PTO - Commuter benefits - Free lunches - Paid parental leave - 401(k) - Employee assistance program If you require reasonable accommodation in completing this application, interviewing, completing any pre-employment testing, or otherwise participating in the employee selection process, please contact us.