Our team’s primary initiatives revolve around the offline machine learning pipelines. We aim to deliver frequent, trusted & stable model releases to Sift customers by continuously evolving our process and tooling. We serve customers across multiple verticals such as online commerce, delivery service, finance, travel sites, etc., and we have customers in both developed and developing countries. Our technology helps protect Internet users from ever-evolving online scams, payment fraud, abusive content, account takeover, etc.  We are a forward-thinking team constantly challenging ourselves and the status quo to push the boundary of machine learning and data science across multiple product offerings at Sift and collaborate with product engineering teams to deliver tangible customer value.

We take pride in our work, not ourselves. Open and constructive feedback is valued and often required to ensure rigor in our work. We love learning, hacking, and sharing our findings. We believe that machine learning is THE way to empower internet-scale businesses to thrive.

What you'll do

• Build massive data pipelines and batch jobs that are part of our model training process using the latest technologies such as Apache Spark, Flink, Airflow and Beam.
• Design and implement end-to-end machine learning products
• Prototype and explore with latest machine learning or analytics technologies such as model serving frameworks, or workflow orchestration engines
• Collaborate with machine learning engineers and data scientists and contribute to internal tooling, experimentation, and prototyping effort
• Simplify, re-architect, and upgrade the existing pipeline technologies
• Lead system design discussions and drive engineering excellence
• Handle practical challenges in ML systems such as feature extraction and definition, data validation, training, monitoring, and management of features and models;

What would make you a strong fit:

• You have a growth mindset and a strong interest to work with real-world machine learning applications and technologies
• You are curious about customer and business needs
• You are open to learning and patient to teach when working with our diverse team members with various backgrounds in engineering and data science
• 3+ years of experience working with large datasets (think TBs of data, 10s of thousands of features) in both batch and streaming environments
• Expert programmer in Java or other object-oriented programming languages
• Experience with python, docker container, k8s, terraform, etc.
• Excellent communication skills and collaborative work attitude
• B.S degree in Computer Science or related field 

A little about us:

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

The Sift engine powers Digital Trust & Safety by helping companies stop fraud before it happens. But it’s not just another anti-fraud platform: Sift enables businesses to tailor experiences to each customer according to the risk they pose. That means fraudsters experience friction, but honest users do not. By drawing on insights from our global network of customers, Sift allows businesses to scale, win, and thrive in the digital era.

Benefits and Perks:

• Competitive total compensation package
• 401k plan
• Medical, dental and vision coverage
• Wellness reimbursement
• Education reimbursement
• Flexible time off