Staff Software Engineer, Inference

<div class="content-intro"><div> <div> <div class="gmail_quote"> <div> <div><span id="m_-113912706363268805m_-2746164444908759431gmail-docs-internal-guid-131e4fb0-7fff-b4e9-ff50-e8cf32449b1b">CoreWeave is The Essential Cloud for AI™. Built for pioneers by pioneers, CoreWeave delivers a platform of technology, tools, and teams that enables innovators to build and scale AI with confidence. Trusted by leading AI labs, startups, and global enterprises, CoreWeave combines superior infrastructure performance with deep technical expertise to accelerate breakthroughs and turn compute into capability. Founded in 2017, CoreWeave became a publicly traded company (Nasdaq: CRWV) in March 2025. Learn more at&nbsp;<a href="https://www.coreweave.com">www.coreweave.com</a>.</span></div> <div>&nbsp;</div> <div>We're proud to be a Living Wage accredited Employer.</div> </div> </div> </div> </div> <p>&nbsp;</p></div><h2><span style="font-size: 12pt;"><strong>What You’ll Do</strong></span></h2> <h3><span style="font-size: 12pt;"><strong>Technical Leadership &amp; Architecture</strong></span></h3> <ul> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Define and drive <strong>multi-service, cross-team architecture</strong> for CoreWeave’s inference platform.</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Lead complex design initiatives spanning <strong>request routing, adaptive scheduling, GPU resource management, and cost-per-token optimization</strong>.</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Set technical direction for <strong>low-latency, high-throughput inference systems</strong> operating under strict P99 SLAs.</span></li> </ul> <h3><span style="font-size: 12pt;"><strong>Performance &amp; Optimization</strong></span></h3> <ul> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Lead development of advanced inference optimizations, including:</span></li> <ul> <li style="font-size: 12pt;"><span style="font-size: 12pt;">micro-batching and dynamic scheduling</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">speculative decoding</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">KV-cache reuse and memory optimization</span></li> </ul> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Drive measurable improvements in <strong>P95/P99 latency, throughput, and GPU utilization</strong> across the platform.</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Establish performance benchmarking frameworks and guide teams in <strong>data-driven optimization strategies</strong>.</span></li> </ul> <h3><span style="font-size: 12pt;"><strong>Reliability &amp; Systems Excellence</strong></span></h3> <ul> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Own system-wide <strong>SLIs/SLOs</strong> and ensure reliability improvements across releases.</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Lead efforts in <strong>capacity planning, autoscaling strategies, traffic management, and failure mitigation</strong>.</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Drive post-incident analysis and ensure systemic improvements across teams.</span></li> </ul> <h3><span style="font-size: 12pt;"><strong>Cross-Team Influence</strong></span></h3> <ul> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Partner with Product, Orchestration, Networking, Storage, and Hardware teams to deliver a <strong>cohesive inference platform</strong>.</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Influence technical decisions across org boundaries and ensure alignment on <strong>architecture, performance, and scalability goals</strong>.</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Serve as a <strong>go-to technical expert</strong> for inference systems and distributed AI workloads.</span></li> </ul> <h3><span style="font-size: 12pt;"><strong>Mentorship &amp; Engineering Excellence</strong></span></h3> <ul> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Mentor senior and mid-level engineers; elevate design, coding, and operational standards across teams.</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Lead cross-team design reviews and ensure high-quality system thinking at scale.</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Raise the bar for <strong>engineering rigor, testing, and observability practices</strong>.</span></li> </ul> <h2><span style="font-size: 12pt;"><strong>What We’re Looking For</strong></span></h2> <ul> <li style="font-size: 12pt;"><span style="font-size: 12pt;">~8–12+ years of experience building <strong>large-scale distributed systems or cloud platforms</strong></span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Proven track record of leading <strong>cross-team technical initiatives at scale</strong></span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Strong coding skills in <strong>Go, Python, or C++</strong></span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Deep expertise in <strong>Kubernetes at production scale</strong>, including orchestration, scheduling, and service design</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Strong understanding of <strong>networked systems, performance optimization, and system design</strong></span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;"><strong>Bachelor’s degree in Computer Science</strong>, Engineering, or a related technical field&nbsp;</span></li> </ul> <h3><span style="font-size: 12pt;"><strong>Inference &amp; Performance Expertise</strong></span></h3> <ul> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Hands-on experience with inference systems, including:</span></li> <ul> <li style="font-size: 12pt;"><span style="font-size: 12pt;">batching and micro-batching strategies</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">caching and memory optimization</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">mixed precision (BF16/FP8)</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">streaming token delivery</span></li> </ul> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Demonstrated ability to improve <strong>tail latency (P95/P99)</strong> and system reliability through metrics-driven engineering</span></li> </ul> <h2><span style="font-size: 12pt;"><strong>Nice to Have</strong></span></h2> <ul> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Contributions to inference frameworks such as <strong>vLLM, Triton, TensorRT-LLM, Ray Serve, TorchServe</strong></span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Experience with <strong>GPU systems and performance optimization</strong> (CUDA, NCCL, RDMA, NUMA, GPU interconnects)</span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Experience leading <strong>multi-team or org-level initiatives</strong></span></li> <li style="font-size: 12pt;"><span style="font-size: 12pt;">Exposure to&nbsp;<strong>large-scale AI/ML infrastructure or hyperscale cloud environments</strong></span></li> </ul> <p>The base salary range for this role is 369,000 to 542,300 PLN. The starting salary will be determined based on job-related knowledge, skills, experience, and market location. We strive for both market alignment and internal equity when determining compensation. In addition to base salary, our total rewards package includes a discretionary bonus, equity awards, and a comprehensive benefits program (all based on eligibility).&nbsp;</p><div class="content-conclusion"><p><em>To fulfill our obligation to protect client data, successful applicants offered employment with CoreWeave will be required to complete a basic criminal record check, conducted in compliance with GDPR. Employment offers are conditional upon receiving satisfactory check results</em></p> <p><strong>What We Offer</strong></p> <p>In addition to a competitive salary, we offer a variety of benefits to support your needs, including:</p> <ul> <li>Family-level Medical Insurance</li> <li>Family-level Dental Insurance&nbsp;</li> <li>Generous Pension Contribution&nbsp;</li> <li>Life Assurance at 4x Salary&nbsp;</li> <li>Critical Illness Cover&nbsp;</li> <li>Employee Assistance Programme&nbsp;</li> <li>Tuition Reimbursement</li> <li>Work culture focused on innovative disruption</li> </ul> <p><em>Benefits may vary by location.&nbsp;</em></p> <p><strong>Equal Opportunity&nbsp;</strong></p> <p><em>CoreWeave is an equal opportunity employer, committed to fostering an inclusive and supportive workplace. All qualified applicants and candidates will receive consideration for employment without regard to race, color, religion, sex, disability, age, sexual orientation, gender identity, national origin, veteran status, or genetic information.</em></p> <p><span style="font-weight: 400;"><strong>Recruitment Agencies</strong></span></p> <p><span style="font-weight: 400;"><em><em data-stringify-type="italic">CoreWeave does not accept speculative CVs. Any unsolicited CVs received will be treated as the property of CoreWeave and your Terms &amp; Conditions associated with the use of CVs will be considered null and void.</em></em></span></p> <p><em><span style="font-weight: 400;"><em data-stringify-type="italic">Any unsolicited CVs sent by your company to us – that is to say, in any situation where we have not directly engaged your company in writing to supply candidates for a specific vacancy – will be considered by us to be a “free gift”, leaving us liable for no fees whatsoever should we choose to contact the candidate directly and engage the candidate’s services, and will in no way establish any prior claim by your company to representation of that candidate should the candidate’s details also be submitted by any other party.</em></span></em></p> <p><strong>Export Control Compliance</strong></p> <p>This position requires access to export controlled information. &nbsp;To conform to U.S. Government export regulations applicable to that information, applicant must either be (A) a U.S. person, defined as a (i) U.S. citizen or national, (ii) U.S. lawful permanent resident (green card holder), (iii) refugee under 8 U.S.C. § 1157, or (iv) asylee under 8 U.S.C. § 1158, (B) eligible to access the export controlled information without a required export authorization, or (C) eligible and reasonably likely to obtain the required export authorization from the applicable U.S. government agency. &nbsp;CoreWeave may, for legitimate business reasons, decline to pursue any export licensing process.</p> <p>&nbsp;</p> <p><strong><em>Updated privacy notice - UK and EU Job Applications&nbsp;</em></strong></p> <p><em>When you apply to a job on this site, the personal data contained in your application will be collected by CoreWeave UK Ltd. (“Controller”), which is located at</em></p> <p><em>Phosphor (6th Floor), 133 Park Street, London, SE1 9EA</em></p> <p><em>and can be contacted by emailing </em><em>careers.eu@coreweave.com</em><em>. Controller’s data protection officer can be contacted at </em><em>privacy@coreweave.com</em><em>. Your personal data will be processed for the purposes of managing Controller’s recruitment related activities, which include setting up and conducting interviews and tests for applicants, evaluating and assessing the results thereto, and as is otherwise needed in the recruitment and hiring processes. Such processing is legally permissible under Art. 6(1)(f) of (i) Regulation (EU) 2016/679 (General Data Protection Regulation (“GDPR”) and (ii) the GDPR as it forms part of the laws of the UK (“UK GDPR”), as necessary for the purposes of the legitimate interests pursued by the Controller, which are the solicitation, evaluation, and selection of applicants for employment. Your personal data will be shared with Greenhouse Software, Inc., a cloud services provider located in the United States of America and engaged by Controller to help manage its recruitment and hiring process on Controller’s behalf. With respect to transfers originating from the UK or the European Economic Area ("EEA") to a country outside the UK or the EEA, we implement the appropriate transfer mechanism(s) and other appropriate solutions to address cross-border transfers as required by applicable law. You may request a copy of the suitable mechanisms we have in place by contacting us at </em><a href="mailto:privacy@coreweave.com"><em>privacy@coreweave.com</em></a></p> <p><em>Your personal data will be retained by Controller as long as Controller determines it is necessary to evaluate your application for employment. Where permitted by applicable law, we may also retain your personal data for a limited period after the recruitment process ends in order to consider you for future job opportunities, respond to legal claims, or comply with record-keeping obligations. Under the GDPR and the UK GDPR, you have the right to request access to your personal data, to request that your personal data be rectified or erased, and to request that processing of your personal data be restricted. You also have the right to data portability. In addition, you may lodge a complaint with the relevant supervisory authority: (i) A list of Europe’s data protection authorities can be found </em><a href="https://urldefense.com/v3/__https://ec.europa.eu/justice/article-29/structure/data-protection-authorities/index_en.htm__;!!I6uDfDBXfA!zaqvpaXitCAqve4cpmPGknjMlTsgIw8w_6xTVeiRpNP5Eo6Ajz9ZkXAYM2uL-nlD8kD6Ndd-Oe-k_BEQQh9xVQGfFw$"><em>here</em></a><em>; and (ii) for the UK, this is the </em><a href="https://urldefense.com/v3/__https://ico.org.uk/__;!!I6uDfDBXfA!zaqvpaXitCAqve4cpmPGknjMlTsgIw8w_6xTVeiRpNP5Eo6Ajz9ZkXAYM2uL-nlD8kD6Ndd-Oe-k_BEQQh9IDhJOUA$"><em>Information Commissioner's Office</em></a><em>.</em><em>&nbsp;</em></p> <p><em>For additional information, please see our </em><a href="https://docs.coreweave.com/docs/policies/terms-of-service/privacy-policy"><em>Privacy Policy</em></a><em>.</em></p></div>