Senior NLP/ML Engineer Offline

We are looking for a Senior NLP/ML Engineer to join our team. As a member of the Engineering team, you will work closely with other data scientists and software engineers as a key player in designing and building state-of-the-art ML decision systems for insurance claim processing.

About Our Customer:

The Сustomer is a leading provider of vehicle lifecycle solutions, enabling the companies that build, insure, repair, and replace vehicles to power the next generation of transportation. The company delivers advanced mobile, artificial intelligence, and connected car technologies through its platform, connecting a vibrant network of 350+ insurance companies, 24,000+ repair facilities, OEMs, hundreds of parts suppliers, and dozens of third-party data and service providers. The customer's collective set of solutions inform decision-making, enhance productivity, and help clients deliver faster and better experiences for end consumers. 

The сustomer’s company was ranked #17 in the Top 100 Digital Companies in Chicago in 2020 by Built in Chicago, an online community for digital technology entrepreneurs in Chicago, and was named one of Forbes best mid-sized companies to work for in 2019 – an important accolade and retention tool for the 2,600+ full-time company employees (alongside 350 dedicated contractors).

The сompany’s corporate headquarters is in downtown Chicago in the historic Merchandise Mart - a certified LEED (Leadership in Energy and Environmental Design) building that is also known to be a technology hub within the broader metro.

About Our Project:

Safekeep is a business unit that focuses on automating insurance claim subrogation for auto, workers compensation, property and general liability claims.

Safekeep leverages data analysis and AI/Machine learning packaged into a smart workflow engine to :

Identify claims with subrogation potential

Minimize the impact of subrogation team turnover

Decrease the administrative costs of subrogation

Simplify and optimize cross-carrier interaction

UI for the smart workflow engine is built specifically for subrogation business processes, bringing together data for decision-making related to the recovery process and tracking. This includes automated processing of demand packages, settlements and payments.

Safekeep provides a digital platform for carrier-to-carrier collaboration to standardize and streamline the subrogation interaction between them.

In 2020 alone, Safekeep won the following awards:

Innovation Championship by Zurich - Safekeep won 1st place out of 1300 solutions from around the world.

Innovation in Insurance awards - Safekeep won the Global Silver Award out of 359 innovations from 45 countries. It was also voted one of "the 3 best innovations at a global level" in InsurTech

Plug and Play Insurance Partners voted Safekeep as the #1 InsurTech

Requirements:

Experience in Machine Learning/ Data Scientist (e.g. ML algorithm selection, feature engineering, model training, hyperparameter tuning, distributed model training, supervised and unsupervised learning implementation, building model pipelines, using Machine Learning tools/libraries/frameworks)

Experience with language modeling (e.g., transformers, Hugging Face, FastText, Named Entity Recognistion, text cleaning)

Advanced knowledge of Python (native, Pandas, ScikitLearn, Tensorflow or Pytorch, PyStats)

Advanced knowledge of SQL and Data Modeling

Experience in study design: power analysis and schema definition

Proficiency in both written and verbal communication, required for a remote and largely asynchronous work environment

Demonstrated capacity to clearly and concisely communicate complex technical, architectural, and/or organizational problems and propose iterative solutions

Experience owning a feature from concept to production, including proposal, discussion and execution

Self-motivated and self-managed with strong organizational skills

English level:

Intermediate+

Nice to Have:

A master’s degree in computer science, mathematics, statistics, or other quantitative fields

3+ years MLOps experience (e.g. model versioning, model and data lineage, monitoring, model hosting and deployment, scalability, orchestration, continuous learning)

Hands-on experience in ETL Development leveraging Python and Spark/Scala

Experience working with AWS big data technologies (Redshift, S3, EMR, Glue, etc.)

Background in financial services including banking, insurance, or an equivalent field

Experience creating orchestration workflows with tools such as Airflow, Kubeflow or AWS Step Functions

DevOps experience (e.g. CI/CD Pipelines, Infrastructure as Code, containers, Agile software development)

Experience working with data streaming technologies (Kafka, Spark Streaming, etc.)

Proven success in communicating with customers (internal and external), other technical teams, and senior management in order to collect requirements, describe data modeling decisions and data engineering strategy

Knowledge of software engineering best practices across the development lifecycle, including Agile methodologies, coding standards, code reviews, source management, build processes, testing and operations

Responsibilities:

The Senior NLP/ML Engineer will be in charge of building and maintaining AI models for insurance decision systems. As such, they should have a commanding knowledge of state-of-the-art AI modeling (linear models, GBM and XGB, neural nets, and their training methods) to build effective models in a fast-paced environment and be familiar with the fundamentals of modeling (probability, bias-variance trade-offs, parameter estimation, and visualization tools, feature importance) for diagnosis and improvement of model pipelines.

Design, develop, and maintain the automation of frameworks for iterative machine learning model development, training, and inference

Provide teams with operational support and develop solutions that provide monitoring, logging, and alerting capabilities

Automate data flows and reporting pipelines

Manage CI/CD infrastructure, including patching and security updates on the infrastructure

Develop and maintain build scripts to automate deployments for multiple environments including dev/test, QA, UAT, and production