[All remote jobs](https://jobicy.com/jobs.md)[![Liftoff logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/c47aea9f-221.png)](https://jobicy.com/company/liftoff.md)[Liftoff](https://jobicy.com/company/liftoff.md) # Senior Staff Software Engineer, Serving Review the role, location requirements, compensation details, and application process before deciding whether this opportunity fits your next career move. [Apply for this job](#job-application)[View company](https://jobicy.com/company/liftoff.md)ShareRemote from[USA](https://jobicy.com/job-region/usa.md)SalaryUSD 219k–310k / yrDepartment[Software Engineering](https://jobicy.com/categories/engineering.md)EmploymentFull TimeExperienceSeniorPublished30 Sep 2026Apply before30 Oct 2026Listing views34Application actions3Application toolkit ## Make your next move. Prepare your resume, explore your fit, and draft a cover letter for this opportunity. AI Summary ## The role, at a glance. This is a senior staff-level software engineering role on Liftoff’s Accelerate Serving team, responsible for mission-critical real-time ad-serving infrastructure. The engineer will build and operate high-throughput, low-latency bid-request and bidding services while improving scalability, reliability, observability, and capacity planning. A major focus is GPU-powered neural-network inference using TensorRT, including profiling bottlenecks in batching, memory, networking, serialization, and GPU utilization. The role also partners closely with machine learning engineers to productionize models, operate low-latency feature stores, and improve experimentation and benchmarking systems. ## Role DNA A quick view of the complexity, pace, ownership and collaboration implied by the job description. ### Job Complexity 5/5EasyHard ### Pace & Pressure 5/5RelaxedFast-paced ### Autonomy Level 5/5GuidedFull ownership ### Communication Load 4/5IndependentCollaborative AI insightThe role requires 10+ years of experience and deep expertise in distributed systems, real-time performance engineering, and production ML inference. It carries end-to-end ownership for services operating at millions of requests per second under strict latency and reliability requirements. ## Salary analysis Estimated compensation compared with the broader US market for similar roles. Estimated job medianMarket rate$264,500US market range$220k–$320k0$352k AI insightThe disclosed US yearly base-salary bands range from $219,000 to $310,000 depending on approved work location. The midpoint across the full disclosed range is $264,500 per year. A competitive US market base-salary range for a Staff/Senior Staff engineer specializing in large-scale low-latency systems and GPU/ML serving is approximately $220,000 to $320,000 annually, excluding equity and benefits. ## Core skills Skills and capabilities most closely associated with this opportunity. [Distributed systems](https://jobicy.com/jobs?search_keywords=Distributed%20systems.md)[Real-time ad serving](https://jobicy.com/jobs?search_keywords=Real-time%20ad%20serving.md)[Low-latency systems](https://jobicy.com/jobs?search_keywords=Low-latency%20systems.md)[High-throughput services](https://jobicy.com/jobs?search_keywords=High-throughput%20services.md)[GPU inference](https://jobicy.com/jobs?search_keywords=GPU%20inference.md)[TensorRT](https://jobicy.com/jobs?search_keywords=TensorRT.md)[Machine learning infrastructure](https://jobicy.com/jobs?search_keywords=Machine%20learning%20infrastructure.md)[Performance optimization](https://jobicy.com/jobs?search_keywords=Performance%20optimization.md)[Feature stores](https://jobicy.com/jobs?search_keywords=Feature%20stores.md)[Go](https://jobicy.com/jobs?search_keywords=Go.md) Sample interview questionsHow would you investigate a latency regression in a real-time GPU inference serving path?I would first segment latency by request type, model version, host, and deployment window, then use distributed tracing and service metrics to isolate time spent in queueing, serialization, network calls, feature retrieval, batching, GPU execution, and response handling. I would compare the affected path with a known-good baseline, reproduce the issue under representative load, and validate a fix with canary deployment and latency-percentile guardrails. What trade-offs would you consider when designing dynamic batching for TensorRT inference? I would balance GPU utilization and throughput against p95/p99 request latency, queue wait time, model shape constraints, and traffic variability. The design should use bounded batching windows, enforce per-request deadlines, and expose controls for batch size and concurrency so the system can adapt without violating exchange latency requirements. How would you design a highly available feature store for online bidding? I would prioritize predictable low-latency reads, horizontal scalability, replication, and graceful degradation. The design would include local or regional caching, clear data freshness guarantees, resilient fallback behavior for missing features, capacity headroom, and comprehensive monitoring for availability, tail latency, staleness, and hot-key behavior. Describe how you would safely launch a new model architecture into a high-volume serving environment. I would establish offline quality and performance benchmarks, validate serving compatibility, and run shadow traffic or replay tests before exposing the model to production decisions. I would then use a staged rollout with experiment cohorts, monitor business metrics alongside latency, error rate, GPU utilization, and resource cost, and retain an immediate rollback path. How do you approach technical leadership when owning a cross-functional infrastructure initiative? I begin by aligning stakeholders on the problem, measurable success criteria, risks, and system constraints. I create an architecture and rollout plan, break work into independently deliverable milestones, communicate trade-offs clearly, and ensure operational ownership through testing, dashboards, runbooks, incident readiness, and post-launch optimization. Opportunity details ## About this role. Liftoff is a leading AI-powered performance marketing platform for the mobile app economy. Our end-to-end technology stack helps app marketers acquire and retain high-value users, while enabling publishers to maximize revenue across programmatic and direct demand. Liftoff’s solutions, including Accelerate, Direct, Monetize, Intelligence, and Vungle Exchange, support over 6,600 mobile businesses across 74 countries in sectors such as gaming, social, finance, ecommerce, and entertainment. Founded in 2012 and headquartered in Redwood City, CA, Liftoff has a diverse, global presence. At Liftoff, we’re solving one of the core problems faced by every mobile app: growth. To do so, we build Machine Learning and Big Data-driven technology that can accurately predict which apps a user will like, and connect them in a compelling way. Our systems operate at a scale unseen outside of the largest Internet companies — processing over 12 million requests per second and interacting with over 5 billion unique users each day. The Serving team builds and maintains the mission-critical infrastructure responsible for serving ads across Liftoff’s product line. As an engineer on Liftoff’s Accelerate Serving team, you will: * Design, build, and operate the high-throughput, low-latency services that receive bid requests, execute Liftoff’s bidding logic, and respond to ad exchanges in real time. * Improve the performance, scalability, and reliability of systems that process 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 to identify and eliminate bottlenecks in 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 and reliable serving implementations. * Design and operate large feature store fleets that provide low-latency access to real-time and precomputed features. * Develop benchmarking and performance-analysis tools that help engineers compare models, understand latency and throughput trade-offs, and identify regressions before deployment. * Improve experimentation tooling that allows machine learning teams to orchestrate offline training runs, evaluate candidate models, and maintain model leaderboards. * Own changes through their full lifecycle—from system design and implementation to testing, deployment, observability, capacity planning, incident response, and continued optimization. Requirements: * Strong core Computer Science fundamentals (data structures, algorithms, system architecture) * 10+ years of industry experience * M.S.. or higher in Computer Science (or equivalent work experience) * Experience with Go is a plus Location: 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 WA We are a remote-first company with US hubs in Redwood City, Los Angeles, and New York City. Travel Expectations: We offer several opportunities for in-person team gatherings, including but not limited to project meetings, regional meetups, and company-wide events. We expect our employees to attend these gatherings at least once per quarter. These gatherings provide essential opportunities for collaboration, communication, and team building. Compensation: Liftoff offers all employees a full compensation package that includes equity and health/vision/dental benefits associated with your country of residence. Base compensation will vary based on the candidate’s location and experience. The following are our base salary ranges for this role: * SF 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 #LI-EL1 Liftoff offers a fast-paced, collaborative, and innovative work environment where employees are empowered to grow and make an impact. We’re shaping the future of the mobile app ecosystem—join us and help accelerate what’s next. Liftoff’s compensation strategy includes competitive salaries, equity, and benefits designed to support employee well-being and performance. We benchmark compensation based on role, level, and location to ensure fairness and market alignment. Benefits may include medical coverage, wellness stipends, and additional perks based on your country of residence. Liftoff is an equal opportunity employer. We are committed to creating an inclusive environment for all employees and applicants regardless of race, ethnicity, national origin, age, marital status, disability, sexual orientation, gender identity, religion, veteran status, or any other characteristic protected by applicable law. Agency and Third Party Recruiter Notice: Liftoff does not accept unsolicited resumes from individual recruiters or third-party recruiting agencies in response to job postings. No fee will be paid to third parties who submit unsolicited candidates directly to our hiring managers or Recruiting Team. All candidates must be submitted via our Applicant Tracking System by approved Liftoff vendors who have been expressly requested to make a submission by our Recruiting Team for a specific job opening. No placement fees will be paid to any firm unless such a request has been made by the Liftoff Recruiting Team and such a candidate was submitted to the Liftoff Recruiting Team via our Applicant Tracking System. Show more [Apply now >](https://jobicy.com/jobs/154260-senior-staff-software-engineer-serving.md) * ![Upload CV](data:image/svg+xml;base64,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) ### Upload your resume now To unlock remote work opportunities and be discovered by global employers. This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content. Next step ## Apply now. Follow the employer’s application method and review Jobicy’s safety guidance before sharing personal information. Keep exploring ## Related remote jobs. * ![saas.group logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/f6d362c3-221-1.png) saas.group Sep 30 New ### [Chief Technology Officer](https://jobicy.com/jobs/154291-chief-technology-officer-4.md) This role is part of our Prerender team, one of our largest brands at saas.group. Prerender is a dynamic rendering SaaS platform within the saas.group portfolio. Since 2017, we’ve revolutionized… * ![Life360 logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2022/02/f269bad3-221.jpeg) Life360 Sep 30 New ### [Senior Backend Engineer II, AI Native, Vertical Experiences](https://jobicy.com/jobs/154259-senior-backend-engineer-ii-ai-native-vertical-experiences.md) About Life360 Life360’s mission is to keep people close to the ones they love. Our category-leading mobile app, Tile tracking devices, and Pet GPS tracker empower members to protect the… * ![Liftoff logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/c47aea9f-221.png) Liftoff Sep 30 New ### [Software Engineer, Partner Engineering](https://jobicy.com/jobs/154262-software-engineer-partner-engineering.md) Liftoff is a leading AI-powered performance marketing platform for the mobile app economy. Our end-to-end technology stack helps app marketers acquire and retain high-value users, while enabling publishers to maximize… * ![Quora logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2020/09/WRILS-200916172339-629302.jpg) Quora Sep 30 New ### [Software Engineer New Grad, Machine Learning Platform – Quora](https://jobicy.com/jobs/154244-software-engineer-new-grad-machine-learning-platform-quora.md) [Quora is a privately held, “remote-first” company. This position can be performed remotely from anywhere in Canada or the United States. Please visit careers.quora.com/eligible-countries for details regarding employment eligibility by… * ![Invisible Technologies logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/5d284c35-221.jpeg) Invisible Technologies Sep 30 New ### [Software Engineer, Agentic AI](https://jobicy.com/jobs/154246-software-engineer-agentic-ai.md) About Invisible Invisible Technologies makes AI work. Our end-to-end AI platform structures messy data, automates digital workflows, deploys agentic solutions, measures outcomes, and integrates human expertise where it matters most…. * ![Windranger Labs logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/6d827f41-221.png) Windranger Labs Sep 30 New ### [Blockchain Engineer 区块链开发工程师](https://jobicy.com/jobs/152074-blockchain-engineer-%e5%8c%ba%e5%9d%97%e9%93%be%e5%bc%80%e5%8f%91%e5%b7%a5%e7%a8%8b%e5%b8%88.md) Who we are Mantle is the entry point for institutions and traditional finance to access real-world assets on-chain. Backed by the world’s largest community-owned treasury of over $4B, Mantle combines… * ![Windranger Labs logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/6d827f41-221.png) Windranger Labs Sep 30 New ### [QA Engineer 区块链测试工程师](https://jobicy.com/jobs/152081-qa-engineer-%e5%8c%ba%e5%9d%97%e9%93%be%e6%b5%8b%e8%af%95%e5%b7%a5%e7%a8%8b%e5%b8%88.md) Who we are Mantle is the entry point for institutions and traditional finance to access real-world assets on-chain. Backed by the world’s largest community-owned treasury of over $4B, Mantle combines… * ![Teachable logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2021/04/Teachable.png) Teachable Sep 30 New ### [Senior Full Stack Engineer II](https://jobicy.com/jobs/152092-senior-full-stack-engineer-ii.md) What is Teachable? Teachable is the platform for experts and businesses who take education seriously. In a world where anyone can ask AI for information, we’re the home for those… * ![Teachable logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2021/04/Teachable.png) Teachable Sep 30 New ### [Engineering Manager](https://jobicy.com/jobs/152085-engineering-manager-6.md) What is Teachable? Teachable is the platform for experts and businesses who take education seriously. In a world where anyone can ask AI for information, we’re the home for those… * ![Playson logo](https://jobicy.com/data/server-nyc0409/galaxy/mercury/2025/06/6f266d9c-221-1.png) Playson Sep 30 New ### [Senior Game Developer](https://jobicy.com/jobs/152046-senior-game-developer.md) About the RoleWe’re looking for a Senior Game Developer to bring fresh ideas, strong technical expertise, and a passion for building high-quality games. This role is ideal for someone who… [Browse all jobs](https://jobicy.com/jobs.md)