Senior Staff Software Engineer, Serving
New
L
LiftoffMobile advertising
This role is eligible for full-time remote work in one of our entities: CA, CO, ID, IL, FL, GA, MA, MI, MN, MO, NJ, NV, NY, OR, PA, TX, UT, and WAFull-TimeStaff
SalarySF Bay Area, NYC, Los Angeles/Orange County: $255,000 - $310,000; Seattle/Olympia, Austin, San Diego, Santa Barbara, Boston: $234,000 - $285,000; All other cities and towns in our approved states: $219,000 - $266,000
Apply NowOpens the employer's application page
Job Details
- Experience
- 10+ years of industry experience
- Required Skills
- AlgorithmsData StructuresGo
Requirements
- Bring strong computer science fundamentals, including data structures, algorithms, and system architecture.
- Have 10+ years of industry experience.
- Hold an M.S. or higher in Computer Science, or have equivalent work experience.
- Experience with Go is a plus.
Responsibilities
- Design, build, and operate high-throughput, low-latency services that process bid requests, execute bidding logic, and respond to ad exchanges in real time.
- Improve the performance, scalability, and reliability of systems processing millions of requests per second under strict latency constraints.
- Develop and optimize GPU-powered inference services that execute neural network models using TensorRT.
- Profile end-to-end inference pipelines and address bottlenecks in GPU utilization, batching, memory access, serialization, networking, and request handling.
- Partner with machine learning engineers to productionize model architectures and features through efficient, reliable serving implementations.
- Design and operate feature store fleets that provide low-latency access to real-time and precomputed features.
- Develop benchmarking and performance-analysis tools to compare models, assess latency and throughput trade-offs, and identify regressions.
- Improve experimentation tooling for offline training runs, candidate model evaluation, and model leaderboards.
- Own system changes from design and implementation through testing, deployment, observability, capacity planning, incident response, and continued optimization.
View Full Description & ApplyYou'll be redirected to the employer's site
