Base Salary
$202k - $224k/yr
Responsibilities
- Design and build highly scalable search and AI-serving infrastructure focused on latency, throughput, reliability, and infrastructure efficiency.
- Develop backend architecture for LLM-based retrieval, ranking, personalization, and generative search.
- Integrate large language models and machine learning models into production search-serving paths.
- Optimize GPU inference and model-serving performance using batching, request routing, caching, streaming, and efficient resource utilization.
- Build LLM-serving infrastructure for context prefill, KV and prefix-cache reuse, progressive generation, and multi-turn or paginated search.
- Develop retrieval and ranking systems spanning lexical retrieval, semantic retrieval, embeddings, structured signals, and ML/LLM-based ranking.
- Build real-time feature retrieval, hydration, caching, and data-processing systems for fresh ranking and model signals.
- Partner with ML engineers and data scientists to productionize ranking and relevance models and improve experimentation velocity.
- Analyze and improve end-to-end search performance across retrieval, feature serving, model inference, orchestration, networking, and presentation hydration.
- Design observability, capacity management, graceful degradation, experimentation, and safe rollout mechanisms.
- Troubleshoot complex production issues and provide technical leadership through architecture discussions, design reviews, code reviews, and mentoring.
Requirements
- 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 latency, throughput, reliability, and infrastructure efficiency.
- Familiarity with distributed data processing and streaming technologies such as Kafka, Flink, or Spark.
- Experience operating production systems, including observability, monitoring, capacity planning, incident response, and reliability engineering.
- Preferred experience with search and recommendation systems, including retrieval, ranking, query understanding, indexing, and personalization.
- Preferred hands-on experience with Elasticsearch, OpenSearch, Solr, Vespa, Lucene, or proprietary search systems.
- Preferred experience with LLM or ML model-serving infrastructure such as vLLM or Triton.
- Preferred experience optimizing GPU inference, including batching, request scheduling, model parallelism, memory management, and GPU utilization.
- Preferred familiarity with LLM serving concepts including prefill/decode, KV caching, prefix caching, streaming generation, speculative techniques, and distributed inference.
- Preferred experience with embeddings, semantic retrieval, approximate nearest-neighbor search, semantic IDs, generative retrieval, constrained decoding, and near-real-time ranking signals.
- Strong system design, problem-solving, analytical, and cross-functional collaboration skills.
Benefits
- San Francisco and Sunnyvale roles offer a base salary of USD $202,000-$224,000 per year.
- Eligible full-time employees may participate in Uber's bonus program and may receive equity awards or other compensation.
- All full-time employees are eligible to participate in a 401(k) plan and various benefits.
Tech Stack
Categories
About Uber
We are Uber. The go-getters. The kind of people who are relentless about our mission to help people go anywhere and get anything and earn their way. Movement is what we power. It’s our lifeblood. It runs through our veins. It’s what gets us out of bed each morning. It pushes us to constantly reimagine how we can move better. For you. For all the places you want to go. For all the things you want to get. For all the ways you want to earn. Across the entire world. In real time. At the incredible speed of now. The idea for Uber was born on a snowy night in Paris in 2008, and ever since then our DNA of reimagination and reinvention carries on. We’ve grown into a global platform powering flexible earnings and the movement of people and things in ever expanding ways. We’ve gone from connecting rides on 4 wheels to 2 wheels to 18-wheel freight deliveries. From takeout meals to daily essentials to prescription drugs to just about anything you need at any time and earning your way. From drivers with background checks to real-time verification, safety is a top priority every single day. At Uber, the pursuit of reimagination is never finished, never stops, and is always just beginning.