Baseten
Baseten
Baseten машиналық оқыту және жасанды интеллект қолданбаларын іске қосатын компанияларға модель инференсі инфрақұрылымын ұсынады. Оның платформасы жоғары өткізу қабілеті бар инференсті, жылдам орналастыруды, автоматты масштабтауды, қауіпсіз корпоративтік модельдерді ұсынуды және ашық бастапқы кодты модельдерді қаптамаға жинауға қолдауды біріктіріп, жылдам әрі ауқымды қызмет көрсетуге арналған. Baseten инженерлік және машиналық оқыту командаларына модель инфрақұрылымының операциялық талаптарын басқаруға көмектеседі, осылайша олар нақты салаға арналған модельдерді әзірлеуге назар аудара алады. Компания жасанды интеллект, SaaS және корпоративтік технологиялар салаларында жұмыс істейді, командасында 11–50 қызметкер бар.

Engineering Manager, GPU Inference Performance at Baseten

Lead GPU inference performance engineering at Baseten, an AI infrastructure company. Guide runtime optimization, model efficiency, and the growth of a specialized technical team.

Сипаттама

  • Manage, mentor, and develop inference performance engineers through regular one-to-ones, feedback, career planning, and performance reviews
  • Recruit GPU and inference engineers while fostering a collaborative team culture
  • Own the runtime performance roadmap and its execution
  • Review technical designs, direct profiling and optimization work, and help engineers assess time and memory use
  • Productionize quantization, speculative decoding, KV-cache reuse, chunked prefill, and custom scheduling
  • Translate performance gains into measurable improvements in tokens per GPU-hour, utilization, latency, and cost
  • Bring new model architectures onto emerging hardware and tune their performance
  • Collaborate with Infrastructure, Inference Platform, Kernels, Model APIs, and customer-facing teams to prioritize work, coordinate launches, and deliver improvements
  • Establish engineering standards for quality, benchmarking, operational excellence, and incident response
  • Advance agentic inference optimization, agentic kernels, speculative-decoding model training, and the Baseten Inference Stack

Талаптар

  • Bachelor’s, master’s, or doctoral degree in computer science, engineering, mathematics, or a related discipline
  • Management experience covering engineering hiring, mentoring, feedback, and performance reviews
  • Experience leading or closely supporting GPU optimization teams in training, inference, or recommendation systems
  • Deep technical knowledge of GPU workloads, architecture, and performance tradeoffs
  • Familiarity with machine learning libraries including PyTorch, TensorRT, or TensorRT-LLM
  • Demonstrated ability to set roadmaps and deliver complex technical projects with a team
  • Strong written and verbal communication skills for aligning stakeholders across teams
  • Familiarity with inference engines such as vLLM, SGLang, or TensorRT-LLM
  • Experience applying LLM optimization methods such as quantization, speculative decoding, and continuous batching
  • Experience developing or working with GPU kernels using CUDA, Triton, or CUTLASS
  • Experience scaling an engineering team during rapid startup growth
  • Prior hands-on experience as a performance or systems engineer before moving into management

Артықшылықтар

  • Competitive compensation package with meaningful equity
  • For U.S. employees, full medical, dental, and vision coverage for employees and dependents
  • Flexible paid time off, including a company-wide winter break
  • Paid parental leave
  • Fertility and family-building support through Carrot
  • For U.S. employees, a company-facilitated 401(k) plan
  • Opportunities to work with a range of machine learning startups and build industry connections

Ұқсас жұмыс орындары

Agilent Technologies

Field Service Engineer, Asset Performance Management — Japan

Agilent Technologies

Install, maintain, and repair Agilent hardware, software, and network solutions. Provide on-site customer support and travel throughout Japan 100% of the time.

Ашу
Agilent Technologies

Field Service Engineer, Asset Performance Management (Japan)

Agilent Technologies

Install, maintain, and troubleshoot enterprise asset performance systems for Agilent customers. The role includes integrated solution delivery, technical training, and 100% travel.

Ашу
Hewlett Packard Enterprise

Senior Channel Presales Technical Architect, Canada

Hewlett Packard Enterprise

Guide channel partners in designing and selling HPE storage and data protection solutions. Build technical advocacy, grow the opportunity pipeline, and support customer engagements.

Ашу
Hewlett Packard Enterprise

Senior Channel Presales Technical Architect, Storage — HPE Canada Remote

Hewlett Packard Enterprise

Help HPE channel partners position, design, and sell storage and data protection solutions. Support solution architecture, demonstrations, proofs of concept, pipeline development, and partner technical advocacy.

Ашу
Hewlett Packard Enterprise

Channel Presales Technical Architect, Canada

Hewlett Packard Enterprise

Guide HPE channel partners in positioning, designing, and delivering storage and data protection solutions. Build partner technical capability, develop pipeline, and help secure competitive wins.

Ашу
Xero

Customer Experience Data Analyst

Xero
1 001 – 5 000 Қызметкерлер
H1B визасының демеушісіB2BSaaS

Create reporting and workforce insights for Xero’s Customer Experience and Payment Operations teams. Use Tableau and Zendesk Explore to inform business reviews, headcount planning, and senior leadership decisions.

Ашу
Hewlett Packard Enterprise
General Dynamics Information Technology

Senior Azure Cloud Data Engineer

General Dynamics Information Technology

Modernize Indian Health Service clinical records by building Azure data pipelines and scalable healthcare data models. Develop ETL workflows and PySpark transformations for enterprise health data.

Ашу
Hewlett Packard Enterprise

Senior Network Operations Cloud Engineer (Secret Clearance)

Hewlett Packard Enterprise

Operate and secure Hewlett Packard Enterprise private-cloud networks supporting federal customers. Troubleshoot classified infrastructure, VMware NSX, ServiceNow changes, and mission-critical connectivity.

Ашу
Sanofi

Senior People Business Partner, Greater China Manufacturing

Sanofi

Advise Sanofi’s Greater China manufacturing and supply chain leaders on people strategy. Lead workforce planning, organizational transformation, talent initiatives, and compliance across multiple sites.

Ашу