Senior Machine Learning Engineer

Description

The company is a global tech firm with more than 25 years of engineering leadership, over 2,000 staff and more than 500 active projects for Fortune 500 clients such as HBO, Microsoft, Google and Starbucks.

It works with enterprise leaders on AI platforms and digital transformation work.

The team is made up of ambitious, collaborative people who keep learning.

The client is a leading provider of vehicle lifecycle software, headquartered in Chicago. Its platform adds mobile, artificial intelligence and automotive technology to help the companies that build, insure and replace vehicles. It links more than 350 insurers, over 24,000 repair shops, hundreds of parts suppliers and dozens of data and service providers, which helps them serve end consumers better.

Responsibilities

• Build end-to-end document intelligence pipelines on AWS
• Create and improve ML models that classify documents, split them into segments and extract fields
• Design data processing systems that handle PDFs of up to 2,000 pages
• Work with subject matter experts to shape and refine extraction requirements
• Take features from research through to production and monitoring
• Set up evaluation frameworks and quality metrics for extraction accuracy

Requirements

• Advanced Python skills, including native Python and libraries such as Pandas, ScikitLearn, TensorFlow or PyTorch, PyStats and Pydantic
• Hands-on use of AWS ML and deployment services such as SageMaker, Lambda, CloudFormation or CDK, and Step Functions
• Advanced SQL and data modelling skills
• Experience with GenAI for document intelligence: prompt engineering, RAG, multi-modal vision and text models, and production deployment on AWS Bedrock or Azure OpenAI APIs
• Experience designing experiments, including power analysis and hypothesis testing
• Strong written and spoken communication, able to explain complex technical problems clearly and propose iterative fixes
• Experience taking a feature from idea to production, covering proposal, discussion and delivery
• Experience with document processing tools such as AWS Textract, Azure Document Intelligence or other OCR and layout detection systems
• Experience with PDF and image processing libraries such as PyMuPDF, OpenCV or Pillow
• Experience in machine learning or data science, such as algorithm selection, feature engineering, model training, hyperparameter tuning, supervised and unsupervised learning, and building model pipelines
• Experience with AWS big data services such as Redshift, S3, EMR and Glue
• English at upper-intermediate level

Conditions

Fully remote role with a largely asynchronous way of working