Senior Staff Software Engineer, Serving in New York at Jobgether
Explore Related Opportunities
Job Description
This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior Staff Software Engineer, Serving based in United States.
This role offers the opportunity to shape mission-critical infrastructure powering real-time advertising at massive global scale. As part of the Serving team, you will design and operate high-throughput, low-latency systems that process millions of requests per second under demanding performance constraints. You will work at the intersection of distributed systems, machine learning infrastructure, GPU computing, and real-time data processing. Your work will directly influence the scalability, reliability, and efficiency of ad-serving platforms used across a global mobile ecosystem. You will collaborate closely with machine learning engineers to bring sophisticated models into production and continuously optimize their serving performance. This is a highly technical role for an experienced engineer who thrives on complex systems, performance optimization, and large-scale infrastructure challenges.
- Design, build, and operate high-throughput, low-latency services that process bid requests, execute real-time bidding logic, and respond to ad exchanges.
- Improve the performance, scalability, and reliability of systems handling millions of requests per second while operating within strict latency requirements.
- Develop and optimize GPU-powered inference services using TensorRT to efficiently execute neural network models in production.
- Profile complete inference pipelines and identify opportunities to optimize GPU utilization, batching, memory access, serialization, networking, and request handling.
- Partner with machine learning engineers to productionize new model architectures and features, translating modeling requirements into efficient, reliable serving implementations.
- Design and operate large-scale feature store fleets providing low-latency access to real-time and precomputed features.
- Build benchmarking and performance-analysis tools that enable engineers to compare models, evaluate latency and throughput trade-offs, and detect performance regressions before deployment.
- Improve experimentation infrastructure that supports offline training runs, candidate model evaluation, and model leaderboards.
- Own engineering changes throughout their complete lifecycle, including system design, implementation, testing, deployment, observability, capacity planning, incident response, and ongoing optimization.
Requirements:
- 10+ years of professional software engineering experience, with a strong track record working on complex, large-scale systems.
- Strong Computer Science fundamentals, including data structures, algorithms, distributed systems, and system architecture.
- M.S. or higher in Computer Science or a related field, or equivalent professional experience.
- Strong ability to design and operate highly scalable, reliable, and performance-sensitive production systems.
- Experience working with machine learning infrastructure, model serving, inference systems, or other high-performance computing environments is highly valuable.
- Strong analytical and performance-engineering skills, with the ability to identify bottlenecks and optimize systems across multiple layers of the stack.
- Ability to collaborate effectively with machine learning engineers and other technical teams to translate research and modeling requirements into production-ready systems.
- Experience with Go is a plus.
- Comfortable taking ownership of technically complex projects from architecture and implementation through production operations and continuous improvement.
Benefits:
- Full-time remote work available across approved US states, including CA, CO, ID, IL, FL, GA, MA, MI, MN, MO, NJ, NV, NY, OR, PA, TX, UT, and WA.
- Competitive base salary based on location and experience.
- Base salary of $255,000–$310,000 for the San Francisco Bay Area, New York City, and Los Angeles/Orange County.
- Base salary of $234,000–$285,000 for Seattle/Olympia, Austin, San Diego, Santa Barbara, and Boston.
- Base salary of $219,000–$266,000 for other cities and towns within approved states.
- Equity as part of the overall compensation package.
- Health, vision, and dental benefits based on country of residence.
- Potential additional benefits such as wellness stipends and other location-specific perks.
- Remote-first work environment with opportunities for in-person project meetings, regional meetups, and company-wide gatherings.
- Expected participation in in-person team gatherings at least once per quarter to support collaboration, communication, and team building.