Skip to main content

Klaviyo

Software Engineer II - Recommendations

Boston, MAFrom $174kmidAdded today

About this role

Klaviyo seeks a Software Engineer II to build and maintain machine learning-based recommendation systems at scale. You'll architect backend services, develop large-scale data pipelines, and collaborate with ML engineers to productionize models while ensuring observability and reliability across multiple channels.

What you'll do

  • Design and evolve backend services powering product recommendations across email, SMS, KAgent, and other channels
  • Build and maintain large-scale data processing pipelines using frameworks like Apache Spark for feature engineering
  • Productionize ML recommendation models by defining interfaces, feature contracts, and deployment patterns
  • Develop vector database infrastructure for recommendation, semantic search, and agentic workflows
  • Implement observability solutions including metrics, logging, tracing, and dashboards for recommendation systems
  • Drive A/B testing and data-driven decision-making to measure recommendation quality and business impact

What they're looking for

  • Backend and distributed systems development
  • Python programming
  • AWS cloud architecture and Kubernetes
  • Large-scale data pipelines (Apache Spark or similar)
  • Relational, analytical, and NoSQL databases
  • A/B testing and data-driven decision making
  • API design and system architecture
  • Production service reliability and performance optimization
Apply on the employer's site

Opens the official application on the employer’s site. No login required.

Klaviyo

Klaviyo builds a platform for personalized mobile app experiences and customer engagement, offering SDKs, identity and access management services, and onboarding solutions. The company is hiring software engineers across mobile development, identity systems, product activation, and internal platform teams.

Website
klaviyo.com
View all jobs at Klaviyo

Likely interview questions

  • Can you walk us through a large-scale data pipeline you've built? What challenges did you face with data quality or performance?
  • Describe your experience productionizing machine learning models. How did you define contracts between data engineers and ML engineers?
Unlock all 7 questions free — and practice them live →