Lead, Recommender Systems Engineering

Raya; United States; Remote; USD 180,000 - 240,000; Full time

Benefits offered by this job

Medical coverage

Dental coverage

Food delivery budget ($50/day)

Equity based employment

Unlimited vacation

Parental leave (12 weeks)

Travel stipend ($1,000/year)

Job summary

Raya is seeking an Engineering Manager for Recommender Systems to lead the backend retrieval and ranking infrastructure powering our recommendations. You will partner with ML leadership to shape the technical strategy and ensure scalable, low-latency systems that delight our members.

The role requires hands-on experience with production recommender systems, a deep product sense, and a track record of building and coaching high-performing teams.

Qualifications

• 3+ years managing engineers with hiring and delivery responsibility.
• Experience leading production recommender systems at scale.
• Hands-on depth in high-throughput, low-latency distributed systems serving millions of users.
• Expertise in Go, Java/JVM, or similar backend language; Postgres, AWS/GCP, and Kubernetes.

Responsibilities

• Build, coach, and retain a high-performing backend team specializing in recommender systems.
• Own reliable, low-latency production systems, observability, and incident response for recommendations.
• Create and execute a technical strategy grounded in product intuition and end-user empathy.
• Partner with ML to define roadmaps balancing user-facing improvements with infrastructure investments.
• Collaborate with Data Science to co-own experimentation processes and best practices.

Skills

Team management

Production recommender systems

Distributed systems

Go

Java/JVM

PostgreSQL

AWS/GCP

Kubernetes

Tools

Elasticsearch/OpenSearch

Vector search

Feature stores

Job description

Raya is seeking an Engineering Manager for Recommender Systems to lead the backend retrieval and ranking infrastructure powering our recommendations. You will partner with ML leadership to shape the technical strategy and ensure scalable, low-latency systems that delight our members.

The role requires hands-on experience with production recommender systems, a deep product sense, and a track record of building and coaching high-performing teams.