Senior Content Discovery & Search Engineer

The Trade Desk; Bellevue (NY); On-site; USD 137,000 - 252,000; Full time

Benefits offered by this job

Comprehensive healthcare (medical, etc

401k plan with company match

Disability coverage

Life insurance

Tuition reimbursement

Parental leave

Paid vacation

13 paid holidays

Employee Stock Purchase Plan

Job summary

The Trade Desk in the United States is seeking a Staff Engineer to own content discovery and search within Ventura TV OS cloud services. You will design, implement, and optimize features that shape how users find and interact with content across the platform.

You will partner with cross-functional teams to ensure performance, relevancy, and scalability of search and recommendation systems, while advancing ML inference and data processing across large catalogs.

Qualifications

• Experience with distributed data processing frameworks and content indexing.
• Hands-on experience in building ML inference and retraining pipelines.
• Familiarity with search systems, ranking, and evaluation techniques.

Responsibilities

• Design, implement, and optimize content discovery and search within Ventura TV OS cloud services.
• Partner with application teams to scale features for performance, relevance, and scale.
• Build high-performance, low-latency search systems for large content catalogs.

Skills

Content discovery

Search systems

ML inference

Distributed data processing

OpenSearch/Elasticsearch

System design

Recommendation systems

Spark/Data pipelines

Tools

OpenSearch

Elasticsearch

Apache Spark

Databricks

Java

Python

TypeScript

Job description

The Trade Desk in the United States is seeking a Staff Engineer to own content discovery and search within Ventura TV OS cloud services. You will design, implement, and optimize features that shape how users find and interact with content across the platform.

You will partner with cross-functional teams to ensure performance, relevancy, and scalability of search and recommendation systems, while advancing ML inference and data processing across large catalogs.