Klarity (Y Combinator S18) uses Natural Language Processing to automate contract review for Revenue Recognition. Our customers include multiple Public companies use Klarity to (1) save time and cost, (2) increase compliance through robust controls, and (3) ease the pain of contract review.
We have spent years working on our core NLP platform and recently decided to focus on the Revenue Recognition use case. Since then we’ve experienced extremely strong growth with Enterprise Software companies and have doubled our revenue in just the last 3 months.
Klarity (YCombinator S18) uses Natural Language Processing to automate contract review for Revenue Recognition. Our customers include companies like Coupa, Okta, RingCentral, Optimizely and Lattice and use Klarity to (1) save time, (2) increase compliance, and (3) ease the pain of contract review.
We have spent years working on our core NLP platform and recently decided to focus on the Revenue Recognition use case. We’ve more than 3xd our ARR in the last 6 months and are on track to 5x in the next 12 months. We are looking for a highly motivated individual who is passionate about our mission and can join our team to make significant contributions to our Machine Learning product. Automating our customer's contracts is absolutely critical to the company as our #1 focus is delivering high-quality machine learning extractions quickly!
Backend: Python
ML Stack: GPT-3, BERT, PyTorch, AllenNLP, Spacy, AWS Textract
Frontend: React
Architecture: Microservice (Docker)
Datastore: MongoDB, S3
CI/CD: Bitbucket -> Jenkins -> ECR
Deployment: AWS ECS Fargate, EC2
Location: Onsite (San Francisco) Or Remote
Job Type: Full-time
Experience: 1-3 years
Responsibilities:
Work with a small team of ML engineers to build machine learning solutions to challenging real world problems such as:
Finding relevant clauses for our customers in their legal documents
Information Retrieval from documents with natural language
Entity Extraction (for example: effective date, duration, payment terms, parties etc.) from legal contracts
Visual Document Information Extraction: Object Detection, Field Extraction from Documents with Variable Structure
Document Classification and Clustering
Accelerating high-quality Labeled Data Gathering.
General ML Ops and Pipeline management
You will love this job if you:
Love solving open-ended operationally and technically complex problems.
Love working across the stack and owning a large part of the codebase.
Thrive in small, cross-functional teams. We are a tightly-knit team of lawyers and engineers, collectively speaking 10 languages!
Are excited to learn about cutting edge advancements in NLP/ML.
Requirements:
Experience using deep learning frameworks such as PyTorch (or its derivatives such as HuggingFace or AllenNLP) or TensorFlow. Experience using common NLP libraries (NLTK, spaCy, Gensim). Strong engineering background with 1-3 years prior machine learning experience. Significant Python backend experience. Excellent communication, presentation and interpersonal skills. Strong work ethic and ability to operate with high velocity.
Nice to haves:
Interest in Linguistics Experience working in LegalTech General ML Ops
We are an equal opportunity employer and value diversity at our company. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status or disability status.
Cool Challenges: Using a mix of statistical and linguistic techniques to perform a high-accuracy information extraction task on "Legalese". Supercharging human lawyers by working closely with lawyers on the team and building useful tools that get deployed immediately. Constructing a robust document processing pipeline that allows for quick onboarding of new contract types and is adaptable to tagset changes.
Stack: Vast majority of the backend codebase is written in python with some internal tools built in javascript. Our Frontend is built in React.js. We use containerized (docker) microservices and host everything on AWS.