Senior Software Engineer - ML&Data Science team

Our Team:

Our ML teams are part of our core Data Science and Machine Learning group and consist of Online and Offline ML teams.

The Online ML team is responsible for building and operating low-latency and data-intensive systems such as a feature store, feature extraction, ML model serving, and versioning systems. 

The Offline ML team is responsible for ML model release process, ML pipelines, model training, and validation.

Tech stack:

- Java

- GCP

- VertexAI

- Flink

- Dataflow

- Dataproc

- Airflow

Opportunities for you:

• Professional growth: quarterly Growth Cycles instead of performance review;
• Experience: knowledge sharing through biweekly Tech Talks sessions. You will learn how to build projects that handle petabytes of data and have small latency and high fault tolerance;
• Business trips and the annual Sift Summit, in 2022, Summit took place in California;
• Remote work approach: you can choose where you work better.

What would make you a strong fit:

• 7+ years of professional software big data development experience;
• Experience building highly available low-latency systems using Java, Scala, or other object-oriented languages;
• Knowledge of GCP or AWS cloud stack for web services and big data processing;
• Basic knowledge of MLOps on model release/training/monitoring;
• Conceptual knowledge of ML techniques;
• B.S. in Computer Science (or related technical discipline), or related practical experience.

Bonus points:

• Experience working with large datasets and data processing technologies for both stream and batch processing, such as Apache Spark, Apache Beam, Flink, and MapReduce;
• Experience solving problems with production systems, and building solutions and automation to prevent them from reoccurring;
• Familiarity with practical challenges in ML systems such as feature extraction and definition, data validation, training, monitoring, and management of features and models;
• Practical knowledge of how to build end-to-end ML workflows;
• Experience with building an ML feature store for batch and real-time aggregation/serving.

What you’ll do:

• Building and operating low-latency and data-intensive systems;
• Designing, implementing, and operating large-scale distributed systems;
• Execute and improve the ML model release process;
• Collaborate with US-based ML teams and work with them in close partnership on core components of Sift products.

A little about us:

Sift is the leading innovator in Digital Trust & Safety.  Hundreds of disruptive, forward-thinking companies like Doordash, Binance, and Twitter trust Sift to deliver an outstanding customer experience while preventing fraud and abuse.

Sift is a series E company with a valuation of $1.7 billion as a unicorn. In 2021, Sift acquired 2 startups: Chargeback and Keyless to extend the company's product portfolio. Sift was nominated as the Best Employer in 2020 in Seattle.

Sift is a big data ML-based platform that processes 70B API requests per month, processes 1PB of data, and tens of thousands of transactions per second.

Let’s Build It Together

At Sift, we are intentionally building a diverse, equitable, and inclusive workplace. We believe that diversity drives innovation, equity is a fundamental right, and inclusion is a basic human need. We envision a place where all Sifties feel secure sharing their authentic selves and diverse experiences with their teams, their customers, and their community – ultimately using this empowerment and authenticity to build trust and create a safer Internet.

This document provides transparency around the way in which Sift handles personal data of job applicants: https://sift.com/recruitment-privacy