Research Engineer / Scientist - Storage for LLM
San Jose, California, United States
USD 136K-359K Entry-level Full Time
Tasks
- Collaborate with inference teams for integration
- Design distributed KV cache system
- Develop cache consistency and synchronization protocols
- Evaluate and extend open-source KV stores or build custom GPU-aware caching layers
- Implement memory-aware sharding eviction and replication strategies
- Monitor system performance and iterate caching algorithms
- Optimize low-latency access and eviction policies
Perks/Benefits
- Competitive salary
- Conference engagement
- Innovative culture
- Open source contribution opportunities
- Research resources
Skills/Tech-stack
AI infrastructure | Batched decoding | CUDA | Caching systems | Distributed Storage | Eviction policies | GPU Programming | Memory Management | Model Parallelism | Open Source | Open source contribution | RDMA | Sharding | System Optimization | System monitoring | Token streaming | Triton
Education
Bachelor's | Master's | PhD
Related jobs
-
Communication optimization | Data parallelism | Deep learning | Distributed Training | GPU AccelerationMid-level Full TimeSeattle, Washington, United States17h ago
-
Software Developer, Scaled Ops AI Acceleration Team USD 147K-203KAI infrastructure | Data Mining | Fine Tuning | Hack | JavaScriptSenior-level Full TimeSunnyvale, CA | Austin, TX | …18h ago
-
Staff Software Engineer, Torch TPU USD 207K-300KCUDA | Computer Vision | Data Processing | Debugging | Distributed SystemsSenior-level Full TimeSunnyvale, CA, USA19h ago
-
C++ | Compilers | Custom Kernels | Data Processing | Data StructuresSenior-level Full TimeMountain View, CA, USA19h ago
-
AI Research Engineer, Computer Vision USD 170K-210KAutoregressive models | CUDA | DDP | Data Pipelines | DeepSpeed401k retirement plan | Company equity | Dental insurance | Fertility support | Human Annotation SupportMid-level Full TimeRemote (U.S. or Canada) R1d ago
-
TL, Research Inference USD 380K-555KBenchmarking | C++ | CUDA | Distributed Systems | GPU ComputingMid-level Full TimeSan Francisco1d ago
-
HPC - AI/ML Platform Engineer USD 113K-190KAnsible | Bash | CI/CD | GPU scheduling | GrafanaDental insurance | Employee resource groups | Flexible family care | Health insurance | Paid HolidaysMid-level Full TimeUnited States R1d ago
-
Staff Software Engineer, Model LifeCycle USD 208K-253KAPI Design | Checkpointing | Distributed Training | Failure recovery | Fine Tuning401k match | Cell phone stipend | Commuter benefits | Dental insurance | Employer HSA contributionsSenior-level Full TimeSan Francisco, CA - US1d ago
-
ML Engineer, II - Road & Lane USD 139K-183KBEV | CUDA | CUDA kernels | Camera Calibration | Computer VisionMid-level Full TimeRemote - US, Ann Arbor, MI, … R1d ago
-
AI infrastructure | Accelerator Virtualization | Container Runtime | Distributed Systems | GPUSenior-level Full TimeSeattle, WA, USA; Kirkland, WA, USA1d ago
-
AI Engineer USD 77K-176KAgentic AI | C Sharp | CUDA | Computer Vision | Deep learningDependent care | Flexible work model | Paid leave | Professional development | Tuition assistanceMid-level Full TimeUSA, CA, El Segundo (101 Continental …2d ago
-
AI Engineer USD 77K-176KAgentic AI | C# | CUDA | Cloud Computing | Computer ScienceDependent care | Paid leave | Professional development | Recognition awards program | Tuition assistanceMid-level Full TimeUSA, DC, Washington (901 15th St …2d ago
-
AI Engineer USD 77K-176KAgentic AI | C# | CUDA | Computer Vision | Deep learningDependent care | Paid leave | Professional development | Tuition assistance | Work-life programsMid-level Full TimeUSA, DC, Washington (901 15th St …2d ago
-
Senior AI Performance and Efficiency Engineer USD 152K-287KAWS | Azure | Bash | CUDA | CUDA programmingSenior-level Full TimeUS, CA, Santa Clara, United States2d ago
-
AI Engineer USD 69K-125KAPI Integration | Autogen | Bias Mitigation | CUDA | ContainerizationSecret clearanceMid-level Full Time6314 Remote/Teleworker US, United States R2d ago
-
Data Solutions Engineer USD 107K-160KAgile Scrum | Amazon Web Services | Apache Beam | Cloud platform | Containerization401k matching | Disability insurance | Life insurance | Medical/Dental/Vision insurance | Paid HolidaysMid-level Full Time6400 LAS COLINAS BLVD IRVING, United …2d ago
-
C++ Engineer (Computer Vision/Embedded Systems) USD 130K-205KAndroid NDK | C++ | CI/CD | CMake | Computer VisionDental insurance | Disability insurance | Employee assistance program | Flexible Paid Vacation | Flexible paid sick leaveSenior-level Full TimeAUT01 - Poly West Parmer Lane …2d ago
-
Physicist/Scientist Machine Learning USD 138K-190KCUDA | Data Preprocessing | Deep learning | Feature Engineering | GPU ComputingFull-time employment | Health and wellbeing programs | Professional development | Relocation assistance | Travel 10 percentMid-level Full TimeSanta Clara,CA, United States2d ago
-
Principal Staff Software Engineer, AI Training Platform USD 207K-340KAutomatic mixed precision | C++ | Container Orchestration | Containerization | Data parallelismCommute to office based on team needs | Hybrid work options | Mentorship and career growth | Work from homeExecutive-level Full TimeMountain View, CA, United States2d ago
-
Senior Specialist AI Engineer - Foundations USD 139K-229KCUDA | Deep learning | Distributed Training | GPU Acceleration | Generative AIHealth and wellness programs | Time awaySenior-level Full TimeSunnyvale, CA, United States2d ago
-
Sr. Staff Software Engineer, AI Infra USD 198K-326KC++ | CUDA | DeepSpeed | Distributed Training | GNNSenior-level Full TimeMountain View, CA, United States2d ago
-
Senior Embedded Software Engineer USD 103K-152KAsyncio | C# | CUDA | Computer Vision | Debugging401k | Commuter benefits | Company events | Flexible PTO | Health and wellness stipendSenior-level Full TimeSan Francisco, CA2d ago
-
Principal Machine Learning Engineer, App SW USD 175K-234KC++ | CUDA | Closed Loop | Closed-loop simulation | ControlHybrid work policy | Mentorship opportunities | Paid time offSenior-level Full TimeSunnyvale2d ago
-
Software Engineer, Systems ML - SW/HW Co-design USD 117K-173KAI infrastructure | C++ | Deep learning | Distributed Systems | GPU ArchitectureSenior-level Full TimeSunnyvale, CA | Pittsburgh, PA | …2d ago
-
Research Scientist, AI Networking (PhD) USD 120K-230KCUDA | Distributed ML | Distributed ML training | GPU Architecture | High PerformanceEntry-level Full TimeMenlo Park, CA2d ago