{"id":2219420,"url":"https://alion.io/job/susquehanna-international-group-gpu-performance-engineer","title":"GPU Performance Engineer","company":{"id":4917,"name":"Susquehanna International Group","domain":"sig.com","url":"https://alion.io/company/sig","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"iCIMS","truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":null,"employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Hong Kong"],"countries":["HK"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"C++","optional":false},{"name":"CUDA","optional":false},{"name":"CUDA Toolkit","optional":false},{"name":"Apache TVM","optional":true},{"name":"ONNX Runtime","optional":true},{"name":"TensorRT","optional":true},{"name":"Triton","optional":true}],"status":"live","first_seen_at":"2026-10-10T12:10:07Z","employer_posted_date":"2026-10-10","last_verified_at":"2026-10-13T05:00:12Z","board_verified":true,"closed_at":null,"days_open":2,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":2},"description":"Overview\nWe are looking for a GPU Performance Engineer to build highly optimized CUDA kernels for low-latency inference. This role is focused on workloads where off-the-shelf runtimes and vendor libraries do not fully exploit the structure of the model, and where custom kernels, memory layouts, and execution strategies can deliver meaningful gains.\nYou will work closely with quantitative researchers and engineers to understand model structure, identify computational bottlenecks, and turn mathematical ideas into production-grade GPU implementations. You will use your understanding of GPU hardware to help shape models that are both mathematically effective and efficient to run. The problems span compact neural networks, tree-based models, and other structured inference workloads where latency, throughput, and efficiency all matter.\nThis role is a strong fit for someone who enjoys low-level optimization, performance analysis, and translating abstract models into hardware-efficient code.\nKey Responsibilities\nDesign, implement, and optimize custom CUDA kernels for latency-critical inference workloads\nDevelop fine-grained GPU implementations tailored to specific model structures\nAnalyze quantitative research models and computational bottlenecks to identify opportunities for parallelization and hardware-efficient execution\nCollaborate directly with quantitative researchers to translate mathematical models into high-performance compute pipelines\nOptimize end-to-end inference performance through kernel tuning, memory-layout design, execution strategy, I/O optimization, and precision tradeoffs\nProfile and benchmark GPU performance \nImprove latency and throughput in production inference systems\nContribute to GPU architecture decisions and performance best practices\nWhat you can expect from us\nReal Impact: By integrating sophisticated coding techniques with innovative engineering ideas, we design and optimize systems that can process massive amounts of data while still ensuring high performance and stability. You’ll see how your contributions towards developing and supporting leading-edge hardware and software technologies make a firm-wide impact that makes us all smarter, faster, and better.\nCollaboration: You will partner closely with our Infrastructure and Strategy Developer Teams to deliver and manage scalable and highly performant systems to support trading in the region and globally.\nGrowth: For many of our roles, we don’t expect you to have prior industry experience in proprietary trading or financial services to succeed at Susquehanna. We’re looking for people who are naturally curious, relentless problem solvers, and have the desire to continuously innovate, learn, and grow.\nBenefits: Susquehanna offers a wide array of competitive employee perks & benefits\nWhat we’re looking for\nStrong proficiency in writing and optimizing CUDA kernels\nSolid programming experience in C/C++ (preferred)\nDeep understanding of GPU architecture, including memory hierarchy, SIMT execution, occupancy, and latency/throughput tradeoffs\nAbility to reason about numerical stability, precision, performance tradeoffs, and how model design choices affect hardware efficiency\nStrong problem-solving skills and comfort working with low-level systems\nPreferred Qualifications\nPhD in Mathematics, Physics, Computer Science, Engineering, or related quantitative field \nStrong background in linear algebra, probability, numerical methods, or scientific computing\nExperience working with quantitative research teams or financial models\nDemonstrated ability to improve real-world inference performance beyond baseline framework or library implementations\nFamiliarity with PTX-level behavior, tensor core utilization, or architecture-specific tuning\nExposure to ONNX Runtime, TensorRT, Triton, TVM, or similar systems\nExposure to:Neural Networks\nTree-based models (e.g. KightGBM)\nState space models (e.g. Mamba architectures)\n\nExperience with kernel fusion, custom operators, model compilation, or graph-level optimization\nAbout Susquehanna\nSusquehanna is a global quantitative trading firm founded by a group of friends who share a passion for game theory and probabilistic thinking. We have incorporated this approach into our culture, where you will find relentless problem solvers within each of our core disciplines: Trading, Technology, and Quantitative Research. From offices around the world, our employees collaborate to make optimal decisions and are driven by the desire to achieve winning results together.\nWhat we do\nWe are experts in trading essentially all listed financial products and asset classes, with a focus on derivatives trading. Through market making and market taking, we handle millions of trading transactions around the world every day, providing liquidity and ensuring competitive prices for buyers and sellers. While our presence in the market is broad, our trading desks are highly specialised, allowing for a deep understanding of unique drivers of each asset class.\nEqual Opportunity Statement\nWe encourage applications from candidates from all backgrounds, and we welcome requests for reasonable adjustments during the recruitment process to ensure that you can best demonstrate your abilities.\nIf you're a recruiting agency and want to partner with us, please reach out to . Any resume or referral submitted in the absence of a signed agreement will not be eligible for an agency fee.\n#LI-DN1 #LI-Onsite","description_format":"text","description_chars":5471,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"phd","optional":true},"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Hedge Funds & Alternative Investments"],"lifecycle":[{"event":"open","at":"2026-10-10T12:10:07Z"}],"visa":[],"liveness":{"score":68,"band":"ok","label":"Likely open","p_open":1,"p_active":0.754,"p_room":0.9,"age_days":2,"expected_fill_days":6,"reasons":["conf:0","win:mid","comp:brand"],"computed_at":"2026-10-13T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/susquehanna-international-group-gpu-performance-engineer","json_url":"https://alion.io/job/susquehanna-international-group-gpu-performance-engineer.json","meta":{"generated_at":"2026-10-13T11:56:22Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":18563,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-14T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":4917},"rest":"https://alion.io/mcp/rest/get_company?id=4917"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fsusquehanna-international-group-gpu-performance-engineer"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fsusquehanna-international-group-gpu-performance-engineer"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fsusquehanna-international-group-gpu-performance-engineer"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/susquehanna-international-group-gpu-performance-engineer\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fsusquehanna-international-group-gpu-performance-engineer"}]}