Senior AI Search Engineer

Uber; Sunnyvale (CA); Vor Ort; USD 202.000 - 224.000; Vollzeit

Benefits dieser Stelle

Bonus program

Equity award

401(k) plan

Various benefits

Zusammenfassung

Uber is seeking Senior Software Engineers for the Search Engineering team in Sunnyvale, CA. You will design and build backend and model-serving infrastructure for AI-powered search experiences, handling high throughput, strict latency, and production reliability.

You will collaborate with ML/data scientists, build LLM-based retrieval and ranking, and optimize GPU inference and serving. Requires 5+ years in backend or distributed systems and strong proficiency in Go/Java/C++/Python.

Qualifikationen

• 5+ years of professional software engineering experience
• Strong programming in Go, Java, C++, or Python
• Experience with large-scale backend or distributed systems
• Experience with high-throughput, low-latency online serving systems

Aufgaben

• Design and build highly scalable search and AI serving infrastructure with a focus on latency, throughput, reliability, and infrastructure efficiency
• Develop the backend architecture for next-generation AI-powered search, including LLM-based retrieval, ranking, personalization, and generative search experiences
• Integrate large language models and machine learning models into production search serving paths while meeting stringent latency and reliability requirements
• Optimize GPU inference and model-serving performance through batching, micro-batching, request routing, caching, and streaming
• Build infrastructure for advanced LLM-serving patterns such as context prefill, KV/prefix-cache reuse, progressive or streaming generation
• Develop scalable retrieval and ranking systems spanning lexical retrieval, semantic retrieval, embeddings, and ML/LLM-based ranking
• Work on semantic-ID and constrained-decoding infrastructure for real-time marketplace signals
• Build and optimize real-time feature retrieval, hydration, caching, and data-processing systems for fresh signals to ranking and LLM models
• Collaborate with ML engineers and data scientists to productionize new ranking and relevance models
• Continuously improve end-to-end search performance by identifying bottlenecks
• Design systems for graceful degradation, observability, capacity management, experimentation, and safe rollouts
• Analyze production metrics to guide system architecture
• Contribute to long-term technical architecture of the Search platform
• Write high-quality production code and provide technical leadership
• Troubleshoot complex production issues and drive improvements

Kenntnisse

5+ years experience

Go

Java

C++

Python

distributed systems

low-latency

Tools

Kafka

Flink

Spark

Elasticsearch

OpenSearch

Solr

Triton

vLLM

Jobbeschreibung

Uber is seeking Senior Software Engineers for the Search Engineering team in Sunnyvale, CA. You will design and build backend and model-serving infrastructure for AI-powered search experiences, handling high throughput, strict latency, and production reliability.

You will collaborate with ML/data scientists, build LLM-based retrieval and ranking, and optimize GPU inference and serving. Requires 5+ years in backend or distributed systems and strong proficiency in Go/Java/C++/Python.