Who Are You
We seek a highly skilled and experienced Staff Software Engineer to join our dynamic and growing ML Engineering team. As a Staff Software Engineer for ML Engineering, you will build platforms that empower fellow engineers and Data Scientists to create market-leading fraud prevention products. We want you to help us lead the scaling of our business, make data-driven decisions, and contribute to our overall ML and data strategy. The ideal candidate must:
- Effectively communicate complex data problems by tailoring the message to the audience and presenting it clearly and concisely.
- Balance multiple perspectives, disagree, and commit when necessary to move key company decisions and critical priorities forward.
- Ability to work independently in a dynamic environment and proactively approach problem-solving.
- Be committed to driving positive business outcomes through expert data handling and analysis.
- Be an example for fellow engineers by showcasing customer empathy, creativity, curiosity, and tenacity.
- Have strong analytical and problem-solving skills, with the ability to innovate and adapt to fast-paced environments.
- Design and build clear, understandable, simple, clean, and scalable solutions.
What You'll Do
- Be an individual contributor who can navigate between design/architecture and execution of the design.
- Modernize Signifyd’s Machine Learning (ML) Platform to scale for resiliency, performance, and operational excellence, working closely with Engineering and Data Science teams across Signifyd’s R&D group.
- Work alongside ML Engineers, Data Scientists, and other Software Engineers to develop innovative big data processing solutions for scaling our core product for eCommerce fraud prevention.
- Take full ownership of significant portions of our ML processing products, including collaborating with stakeholders on machine learning models, designing large-scale data processing solutions, creating additional processing facets and mechanisms, and ensuring the support of low-latency, high-quality, high-scale decisioning for Signifyd’s flagship product.
- Own the significant advancement of our model training and data processing ecosystem, including the evolution of our feature stores and data processing pipelines.
- Architect, deploy, and optimize ML and Data solutions on AWS, developing scalable data processing solutions to streamline data operations and analysis and enhance data solution deployments.
- Implement data and ML processing solutions for offline, batch, and real-time use cases.
- Mentor and coach fellow engineers on the team, fostering an environment of growth and continuous improvement.
- Identify and address gaps in team capabilities and processes to enhance team efficiency and success.
- Automate monitoring of model performance and user behavior.
- Influence the tooling, frameworks, and ML practices with the ML teams.
What You'll Need
- Ideally has 5-10 years of experience in data/ML engineering, including at least five years of experience as a software or machine learning lead. Have successfully navigated the challenges of working with large-scale data processing systems.
- Deep understanding of data processing, comfortable working with multi-terabyte datasets, and skilled in high-scale data ingestion, transformation, and distributed processing, with strong Apache Spark experience.
- Experience in building low-latency, high-availability data stores for use in real-time or near-real-time data processing with programming languages such as Python, Scala, Java, or JavaScript/TypeScript, as well as data retrieval using SQL and NoSQL.
- Hands-on expertise in data technologies with proficiency in Spark, Airflow, Databricks, AWS services (S3, EMR, SQS, Kinesis, etc.), and Kafka. Understand the trade-offs of various architectural approaches and recommend solutions suited to our needs.
- Significant experience in programming languages such as Java, Python, or Scala and experience understanding Cloud infrastructure environments including Kubernetes and Serverless.
- Working knowledge of ML algorithms, clustering algorithms, and binary classifiers (such as XGBoost)
- Experience using feature stores: homegrown solutions or commercial and open-source products like Tecton and Chronon.
- Experience with the latest technologies and trends in Data, ML, and Cloud platforms.
- Demonstrable ability to lead and mentor engineers, fostering their growth and development.
- You have successfully partnered with Product, Data Engineering, Data Science, and Machine Learning teams on strategic data initiatives.