About the opportunity

The Machine Learning Engineer will play a direct role in our objective to build and design a machine learning system that will change the way our users look at documents. Through machine learning, you will translate between NLP and structured computable graphs as well as build out a robust set of tools to enhance our platform.

This is a great opportunity for someone who wants to join a growing R&D organization to build tools and frameworks to help scale our efforts. 

The Machine Learning Engineer will report directly to the Director of Machine Learning and the location is flexible.*

What you’ll do

• Collaborate: Collaborate with our product team to build ML-enabled tools that help our end users work with increased accuracy while simultaneously driving down the cost associated with processing routine legal contracts
• Legal Intelligence: Work cross-functionally to understand the structure and anatomy of critical legal documents and apply this anatomy to develop legal intelligence and automation
• Modeling: Train and optimize machine learning models using a variety of tools and frameworks
• Engineering: Build tools and frameworks to train, store, serve, and analyze machine learning models 
• Data Systems: Work with our data infrastructure team to help build and maintain data systems (we run on Heroku and AWS)

What you’ll bring

• Experience: 4+ years of industry work experience
• Relevant programming experience: excellent knowledge of Python for data analysis, data processing, and server programming. We use numpy, pandas, spacy, NLTK, scikit-learn, pytorch, tensorflow, keras, and many other libraries. This is our preferred tech stack, but if you have comparable experience in a different stack that's fine too.
• Applied science skills: relevant experience with machine learning, natural language processing, neural networks, computational linguistics, knowledge graphs, or taxonomies
• Domain expertise: experience with text classification, key-phrase extraction, question answering, word embeddings, representation learning, neural machine translation, language modeling, text summarization, text generation, and/or knowledge graphs is a plus
• Proficiency with data technology: strong skill set and experience using modern data technologies (SQL, Snowflake, Postgres, Spark, Dask, Pandas)