Senior Data Scientist-Analytics-21-0161
We are Relativity. A market-leading, global tech company that equips legal and compliance professionals with a powerful platform to organize data, discover the truth, and act on it. The US Department of Justice, 199 of the Am Law 200, and more than 329,000 enabled users trust Relativity during litigation, internal investigations, and compliance projects.
Our SaaS product, RelativityOne, has become the fastest-growing product in the company's history and we have consistently been named a great workplace. As we grow, we continue to seek individuals that will bring their whole, authentic self to our team.
We believe that great talent is not bound by geography and that what you do matters more than where you do it. Relativity has assumed a hybrid work strategy, allowing choice and flexibility for employees to work either from home, a physical Relativity office location (once safe to do so), or a combination of the two, within certain logistical boundaries. Submit your application to learn more from our recruiters or contact us for more details.
The Senior Data Scientist will develop machine-learning-driven products for the e-Discovery and Financial Compliance industries in close collaboration with product leaders and engineers. You will use your experience in NLP to build models and solve problems involving big data and privacy concerns.
Relativity is investing heavily in AI -- you will have an opportunity to shape the culture, best practices, and vision of how machine learning and AI are utilized at Relativity. You’ll have the freedom to experiment with and participate in deciding which big data, deep learning and NLP tools are right for Relativity, such as Spark, PyTorch, TensorFlow, SpaCy or AllenNLP.
- Develop machine-learning models and algorithms to be released as new product features.
- Collaborate with engineers to develop production-level code and contribute to the entire deployment lifecycle.
- Contribute to developing internal standards, processes and tooling for a new data science team.
- Collaborate with Product to assemble datasets for evaluation and model-building.
- Experience with privacy-preserving machine learning for NLP applications such as differential privacy or model building on encrypted data.
- Experience building NLP solutions at scale, on datasets of 1 to 100 million texts.
- Legal industry experience, or interest in the legal industry.
- 5 years of data science experience in a business setting, OR 3 years of data science experience in a business setting with data science education (e.g., advanced degree, certifications, coursework, bootcamp, mentored projects).
- Successfully implemented and deployed machine-learning models that realized material business impact, and contributed to the entire lifecycle of the models from data acquisition to model monitoring and updating.
- Experience solving problems in NLP, such as but not limited to: text segmentation, text classification, conceptual similarity metrics, entity extraction, transfer learning, cross-lingual transfer, natural language generation.
- Experience building and deploying machine-learning models on a cloud platform such as AWS, GCP or Azure.
- Proficient in object-oriented programming and scripting in a language such as Python.
- Comfortable with command-line tools.
- Intentional communicator – uses inclusive language whenever possible, communicates data science concepts to colleagues of all backgrounds, uses technical vocabulary judiciously and with intention