Senior Software Engineer - AI Inference Performance
Tasks
- Build and optimize performance critical CUDA kernels
- Build speed of light and roofline performance models
- Collaborate across model framework kernel and hardware teams
- Establish benchmarks and performance regression gates
- Lead analysis of LLM VLM inference workloads
- Optimize inference servers and model execution
- Optimize latency throughput efficiency and scale
- Profile workloads and eliminate bottlenecks
- Tune serving hyperparameters and optimization techniques
Perks/Benefits
- N/A
Skills/Tech-stack
Batching | C++ | CUDA | CUDA Graphs | CUDA kernels | Cache Management | Cutlass | Distributed Systems | GPU Architecture | KV cache | KV-cache management | Memory hierarchy | Microbenchmark | Model Parallelism | NCCL | NVIDIA Nsight | NVIDIA Nsight Compute | Networking | Nsight Compute | Nsight Systems | Numerical Formats | Nvidia NSight Systems | Occupancy | PyTorch | Python | Quantization | Roofline model | Rust | SGLang | Speculative decoding | Speed of Light Modeling | Synchronization | Tensor cores | TensorRT-LLM | Triton | VLLM
Education
Regions
Countries
States
Related jobs
-
Lead AI Data Engineer – Platform & Analytics BRL 40K-40KAWS Athena | Apache Airflow | Apache Iceberg | DAGs | DBT CoreSenior-level Full TimeUS,CA,Santa Clara1d ago
-
C# | C++ | Cloud Computing | Data Management | Distributed SystemsSenior-level Full TimeUS, CA, Santa Clara1d ago
-
Senior-level Full TimeUS, CA, Santa Clara R2d ago
-
Automation | CI/CD | Command Line | Command-line Interface | Continuous integrationEquity | Hybrid workSenior-level Full TimeUS, CA, Santa Clara2d ago
-
Senior Applied AI Engineer, Product Simulation USD 184K-287KAI | Agent Design | CI/CD | Firmware | Human-in-the-loopSenior-level Full TimeUS, CA, Santa Clara2d ago
-
Lead ASIC Package Design Automation and AI Engineer USD 160K-264K2.5D IC | 3D-IC | Artificial Intelligence | Auto-routing | C++Senior-level Full TimeUS,CA,Santa Clara2d ago
-
Staff/Sr. Staff AI Engineer - IT Business Applications USD 145K-235KAWS | Agile | Azure | CI/CD | Distributed SystemsSenior-level Full TimeSanta Clara, CA3d ago
-
AWS | Adversarial Training | Agent systems | Autonomous Agents | AzureSenior-level Full TimeSanta Clara, CA3d ago
-
Senior Deep Learning Software Engineer, DLSim USD 152K-241KArchitectural simulation | C# | C++ | Compiler infrastructure | Compiler optimizationEquity | Health benefits | Paid time offSenior-level Full TimeUS, CA, Santa Clara3d ago
-
Architecture Search | CUDA | CUDA Compilation | CUDA kernel | GPU ProfilingSenior-level Full TimeUS, CA, Santa Clara R3d ago
-
Senior Software Engineer - Cloud Data Platform USD 140K-160KAWS | Alerting | Azure | CI/CD | Cause analysis401k | Dental insurance | Employee referral program | Health savings account | Life insuranceSenior-level Full TimeSanta Clara, CA5d ago
-
Software Engineer (Applied AI/ML) USD 200K-250KCI/CD | Data Pipelines | Data ontologies | Design of Experiments | Digital Twins401k | Bonuses | Equity | FSA | Flexible time offMid-level Full TimeSanta Clara, CA or Remote R5d ago
-
Principal Software Engineer (Data Platform Prisma AIRS) USD 147K-237KAirflow | Apache Beam | Apache Spark | Batch Processing | BenchmarkingSenior-level Full TimeSanta Clara, CA6d ago
-
Senior Solutions Architect, Inference Service Providers USD 184K-287KAgent Design | Cache Management | Custom Inference Kernels | Data Curation | DevOpsSenior-level Full TimeUS, CA, Santa Clara R6d ago
-
Array computing | Asynchronous programming | C++ | CUDA | Compiler optimizationBenefits | EquitySenior-level Full TimeUS, CA, Santa Clara R6d ago
-
Senior Software Engineer, RL Post-Training Frameworks USD 184K-287KActor Based Programming | C# | C++ | Deep learning | Distributed SystemsSenior-level Full TimeUS, CA, Santa Clara R6d ago
-
AWS | Azure | C# | C++ | Computer VisionEntry-level InternshipUS,CA,Santa Clara R6d ago
-
AWS | Azure | C# | C++ | Computer VisionHybrid or onsite workEntry-level InternshipUS,CA,Santa Clara R6d ago
-
Senior-level Full TimeUS, CA, Santa Clara R7d ago
-
API Gateway | Asynchronous programming | Celery | Data Transformation | EnvoySenior-level Full TimeSanta Clara, CA7d ago
-
Senior Software Engineer, Metropolis Vision AI USD 224K-356KAlgorithms | Asynchronous I/O | C++ | CUDA | Computer VisionSenior-level Full TimeUS, CA, Santa Clara7d ago
-
Senior AI Infrastructure Software Engineer - DGX Cloud USD 184K-287KC# | C++ | Cause analysis | Debugging | Distributed SystemsBenefits | EquitySenior-level Full TimeUS, CA, Santa Clara R7d ago
-
Member of Technical Staff - Agent Platform (Agent OS) USD 190K-250KAPI Design | Agentic Orchestration | Authentication | Authorization | Backend EngineeringSenior-level Full TimeSanta Clara HQ8d ago
-
Senior-level Full TimeUS, CA, Santa Clara R8d ago
-
Senior/Staff Machine Learning Engineer, Motion Planning USD 130K-220KC++ | Cloud Computing | Computer Vision | Data Ingestion | Data Ingestion Pipelines401k plan | Free lunch | Professional development | Unlimited beverages | Unlimited snacksSenior-level Full TimeSanta Clara, CA9d ago