Senior ML Engineer: Scalable Recs & Search

7Seventy; United States; Hybrid; USD 221,000 - 405,000; Full time

Job summary

7Seventy is seeking a Senior Machine Learning Engineer to design and maintain large-scale ML systems that power recommendations, search optimization, and content labeling on a distributed social platform. You will own production-grade models and work across data pipelines and real-time inference.

The role emphasizes experimentation, scalability, and cross-team collaboration, with potential on-site components and flexible compensation based on location and experience.

Qualifications

• 3+ years of recent machine learning or data science experience.
• Strong Python proficiency and experience with PyTorch.
• Experience with large-scale, distributed data processing.
• Familiarity with Go, Ray, BigQuery, or Postgres is a plus.
• Excellent communication and collaboration skills.

Responsibilities

• Design and implement machine learning models to improve personalized recommendations, search relevance, spam detection, and topic classification.
• Work with large-scale datasets, including complex social graph data and user-generated content.
• Run experiments and A/B tests, document findings, and iterate on model performance.
• Ensure algorithms deliver accurate recommendations and optimized user experiences.
• Train, retrain, and monitor models to maintain long-term effectiveness.
• Deploy and operate machine learning systems in high-scale production environments.
• Collaborate with engineering teams to integrate ML systems into distributed architecture.

Skills

ML experience

Python

Experimentation

Distributed systems

Communication

Team collaboration

Tools

PyTorch

Ray

BigQuery

Postgres

Golang

Job description

7Seventy is seeking a Senior Machine Learning Engineer to design and maintain large-scale ML systems that power recommendations, search optimization, and content labeling on a distributed social platform. You will own production-grade models and work across data pipelines and real-time inference.

The role emphasizes experimentation, scalability, and cross-team collaboration, with potential on-site components and flexible compensation based on location and experience.