We're Proof, a fast-growing startup in the legal tech industry. Our best-in-class legal services platform is used by thousands of law firms throughout the US, and we've recently raised our Series B from top-tier investors. We're looking for a talented Machine Learning Engineer to join our world-class team and drive the application of AI and ML to make our operations more efficient. This is an exciting opportunity to be the first Data Scientist at a rapidly scaling company and work closely with our CTO and VP of Product.
At Proof, we believe in the power of experimentation and data-driven decision making. While we don't see AI as a silver bullet, we are convinced that our unique position in the legal industry provides us with a real use case where this technology can drive immense business value and become our competitive advantage. Our extensive dataset of legal documents and deep understanding of the legal domain puts us in a prime position to harness AI and ML to streamline our operations and provide unparalleled service to our clients.
As our first Data Scientist, you will have the opportunity to shape our AI strategy from the ground up. You will work on complex problems, influence the tools and techniques that we use each day, and see the direct impact of your work on our business and customers. If you're excited about applying your skills to real-world challenges and being at the forefront of AI innovation and application in the legal industry, this is the perfect role for you.
What you'll do:

• Develop and optimize NLP, NER, and classification models to automatically extract information from legal documents, reducing manual transcription.
• Collaborate with engineering to build data pipelines and deploy, monitor, and maintain ML models into our production environments using tools such as Jupyter Notebook, Docker, and Kubernetes.
• Conduct statistical analysis, including descriptive statistics and predictive modeling, on our business data to generate actionable insights and guide pricing experiments using tools like Pandas, NumPy, and Scikit-Learn.
• Perform outlier analysis to identify and handle anomalies in our datasets, ensuring data quality and model robustness.
• Create informative data visualizations to communicate complex findings and aid in decision-making processes using libraries like Matplotlib, Seaborn, and Plotly.
• Utilize probabilistic graphical models and Bayesian statistical modeling techniques where appropriate to model uncertainty and make probabilistic predictions.
• Fine-tune and adapt existing ML models for our specific use cases, balancing performance and cost-effectiveness.
• Maintain and optimize our data warehouse and ETL pipelines to ensure data quality and availability (we use Airbyte and BigQuery).
• Stay updated with the latest advancements in ML and data science research, applying relevant techniques to enhance our solutions.

What we'll expect you to know on day one:

• 3 years of professional experience working in data science, machine learning, or a related field.
• Strong proficiency in Python and experience with relevant NLP & deep learning libraries (e.g. TensorFlow, PyTorch, spaCy).
• Solid understanding of ML techniques and experience with tasks like information extraction and document/text classification.
• Ability to perform descriptive and predictive statistical analysis, outlier analysis, and data visualizations using tools like SQL, Spark, and Hadoop.
• Experience with development and deployment tools such as Git, Jenkins, and AWS/GCP/Azure.
• Familiarity with probabilistic graphical models and Bayesian statistical modeling.
• Familiarity with agile development methodologies and collaborative tools like Jira or Linear.
• Excellent communication skills and ability to collaborate cross-functionally.
• Self-starter mindset and excitement about applying ML to real-world business problems.

Great to have, but not required:

• Advanced degree in Computer Science, Statistics, or a related quantitative field.
• Familiarity with optimization techniques to balance the needs of multi-sided marketplaces.
• Expertise using OCR to extract data from large PDF documents.
• Previous experience working on a Marketplace tech product.

Benefits:

• Full-time, salary position
• Fully remote, work from anywhere in the US or Canada
• Flexible paid time off and paid holidays
• Phone and Internet monthly stipend
• Equipment provided
• Medical, dental, vision, disability insurance, and 401k available

Compensation:

• Salary range $130,000-$160,000 based on experience and location
• Eligible to participate in company bonus plan

E-VerifyThis company participates in E-Verify, for more information view the Participation and Right to Work Posters.
Application Deadline:

• June 29, 2024