Senior AI Search Engineer: Scalable LLM-Powered Backend

Uber Technologies Inc.; San Francisco (CA); On-site; USD 202,000 - 224,000; Full time

Benefits offered by this job

Bonus program

Equity

401(k) plan

Benefits

Job summary

Uber Technologies Inc. seeks Senior Software Engineers for the Search Engineering team in San Francisco and other US locations. You will design and build AI-powered search infrastructure, optimize GPU inference, and integrate LLMs with production search paths.

Expect high throughput, low latency systems, observability, and collaboration with ML and data teams. Role emphasizes scalable backend architecture, real-time signals, and safe, reliable deployments.

Qualifications

• 5+ years of professional software engineering experience building large-scale backend or distributed systems.
• Strong programming skills in Go, Java, C++, Python, or a similar language.
• Strong understanding of distributed systems, service-oriented architectures, concurrency, networking, caching, and data consistency.
• Experience building high-throughput, low-latency online serving systems.
• Experience with search, recommendation, ranking, machine learning serving, or other large-scale data-intensive systems.
• Experience diagnosing and optimizing system performance across latency, throughput, reliability, and infrastructure efficiency.
• Familiarity with distributed data processing and streaming technologies such as Kafka, Flink, Spark, or similar frameworks.
• Experience operating production systems, including observability, monitoring, capacity planning, incident response, and reliability engineering.
• Strong system design, problem-solving, and analytical skills with the ability to work across multiple layers of a complex production stack.

Responsibilities

• 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, streaming, and efficient resource utilization.
• Build infrastructure for advanced LLM-serving patterns such as context prefill, KV/prefix-cache reuse, streaming generation, and multi-turn search experiences.
• 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 that allows generative models to interact safely with large-scale search catalogs and real-time signals.
• Build real-time feature retrieval, hydration, caching, and data-processing systems that provide fresh signals to ranking and LLM models.
• Partner with ML engineers to productionize ranking/relevance models and speed up experimentation.
• Improve end-to-end search performance by identifying bottlenecks across retrieval, feature serving, model inference, orchestration, and networking.
• Design systems for graceful degradation, observability, capacity management, experimentation, and safe production rollouts of AI and search capabilities.
• Analyze production and experiment metrics to guide system architecture and business trade-offs.
• Contribute to the long-term technical architecture of the Search platform toward AI-native search.
• Write high-quality production code and provide technical leadership through reviews and mentoring.
• Troubleshoot production issues across distributed search and AI-serving systems and drive improvements.

Skills

5+ years experience

Go

Java

C++

Python

distributed systems

low-latency

observability

production systems

problem solving

Tools

Kafka

Flink

Spark

Elasticsearch

OpenSearch

Solr

Lucene

Vespa

vLLM

Triton

Job description

Uber Technologies Inc. seeks Senior Software Engineers for the Search Engineering team in San Francisco and other US locations. You will design and build AI-powered search infrastructure, optimize GPU inference, and integrate LLMs with production search paths.

Expect high throughput, low latency systems, observability, and collaboration with ML and data teams. Role emphasizes scalable backend architecture, real-time signals, and safe, reliable deployments.