Staff Engineer, Inference Optimizations
Tasks
- Benchmark inference engine performance
- Collaborate with product teams to deliver inference features
- Contribute to open source AI infrastructure
- Develop quantization techniques for inference
- Drive hardware and software integration for GPUs
- Identify kernel fusion opportunities
- Implement advanced parallelization across multi node GPU clusters
- Lead design reviews and technical mentorship
- Lead inference performance architecture
- Optimize GPU kernels for attention layers
- Optimize memory and precision management
- Tune MoE expert gateway router kernels
Perks/Benefits
- Conference reimbursement
- Education reimbursement
- Employee assistance program
- Flexible time off
- LinkedIn Learning access
- Local Employee Meetups
- Training reimbursement
Skills/Tech-stack
AMD GPU | Artificial Intelligence | Attention Mechanisms | Bandwidth Optimization | CUDA | CUDA kernel | Compute Utilization Optimization | Compute utilization | Distributed Systems | FP4 | FP8 | FlashAttention | GPU Programming | High Performance | High-Performance Computing | INT8 | Kernel Fusion | Language Models | Large Language Models | MOE | Memory bandwidth | Memory bandwidth optimization | Mixture of Experts | NVIDIA GPU | OpenAI Triton | OpenAI Triton Compiler | Parallel Computing | Performance Computing | Quantization | RMSNorm | ROCm | TensorRT | Triton | Triton Compiler | Utilization Optimization
Education
N/A
Related jobs
-
AI Developer Builder USD 140K-180KAWS | Agentic Systems | Anthropic Bedrock | Context pipelines | DatadogDirect input on roadmap | High ownershipSenior-level Full TimeTel Aviv-Yafo, Tel Aviv District, IL R5h ago
-
Artificial Intelligence Machine Learning Engineer USD 98K-163KArtificial Intelligence | CI/CD | Docker | Elasticsearch | FastAPIHealth insurance | Holiday pay | Learning and development | Life insurance | Long-term disabilitySenior-level Full TimeUSA-VA-Ashburn5h ago
-
CDN | Cloud infrastructure | Dashboards | Data Modeling | Data PipelinesEntry-level Full TimeSeattle, Washington, United States5h ago
-
CUDA | Computation graphs | Deep learning | Language Models | Large Language ModelsEntry-level Full TimeSan Jose, California, United States5h ago
-
AI Software Engineer USD 260K-260KAI Search | API Integration | Agent Orchestration | Azure AI | Azure AI SearchCareer growth | Healthcare | On-site childcare | PTO | Paid HolidaysSenior-level Full TimeTexas-Dallas-5323 Harry Hines Blvd5h ago
-
Compression | Data Engineering | Data Pipelines | Distributed Systems | High AvailabilitySenior-level Full TimeSan Jose, California, United States5h ago
-
AI/LLM Network Software Development Engineer USD 207K-368KAI communication | AI communication frameworks | Communication frameworks | Distributed Systems | High PerformanceEntry-level Full TimeSeattle, Washington, United States5h ago
-
DPO | DeepSpeed | Distributed Training | Evaluation Pipelines | Human preference learningEntry-level Full TimeSan Jose, California, United States6h ago
-
C++ | Clustering | Computer Vision | Data Mining | DeduplicationGrowth opportunities | Team collaborationEntry-level Full TimeSeattle, Washington, United States6h ago
-
C++ | Clustering | Computer Vision | Content deduplication | Data EngineeringEntry-level Full TimeSan Jose, California, United States6h ago
-
Software Engineer, MTIA SW Tooling Engineer USD 141K-208KC++ | CUDA | CUDA GDB | Cuda Memcheck | DWARFSenior-level Full TimeBellevue, WA | Menlo Park, CA …6h ago
-
Agent systems | Artificial Intelligence | Data Curation | Data Generation | Data PipelinesSenior-level Full TimeMenlo Park, CA6h ago
-
Artificial Intelligence | Data Processing | Data debugging | Embedding Models | Fine TuningSenior-level Full TimeMountain View, CA, USA7h ago
-
Computer Vision | Data Analysis | Data Preparation | Debugging | Information RetrievalSenior-level Full TimeMountain View, CA, USA7h ago
-
Software Engineer, Model Inference, DeepMind USD 207K-300KCUDA | Caching | Distributed Systems | GPUs | Hardware accelerationSenior-level Full TimeLondon, UK; Mountain View, CA, USA7h ago
-
Senior Software Engineer, AI/ML GenAI, Core USD 174K-252KC++ | Code review | Computer Vision | Data Processing | DebuggingSenior-level Full TimeNew York, NY, USA7h ago
-
Senior Software Engineer, AI/ML, Creative Intelligence USD 174K-252KAd optimization | Algorithms | C++ | Data Processing | Data StructuresSenior-level Full TimeMountain View, CA, USA7h ago
-
Artificial Intelligence | C# | C++ | Code review | Control SystemsMid-level Full TimeMountain View, CA, USA7h ago
-
Lead Applied AI & Machine Learning Engineer USD 177K-215KAPI | Agentic AI | Bias Testing | Continuous integration | Data ContractsSenior-level Full TimePlano, TX, United States13h ago
-
Machine Learning Engineer, API Multicloud USD 295K-445KAPIs | AWS | Data Pipelines | Data Structures | Data structures algorithmsSenior-level Full TimeSan Francisco14h ago
-
Senior Machine Learning Engineer, Ads ML Platform USD 216K-303KAnomaly Detection | Data Governance | Data Infrastructure | Data Lineage | Data Storage401k employer match | Caregiving support | Comprehensive healthcare benefits | Family planning support | Flexible remote workSenior-level Full TimeRemote - United States R17h ago
-
Applied AI Engineer - iCloud Data USD 150K-220KAI Foundry | Apache Flink | Apache Kafka | Azure AI | Azure AI FoundrySenior-level Full TimeCupertino; Seattle18h ago
-
Applied AI Engineer - iCloud Data USD 150K-220KAWS | Agent Frameworks | Agent coordination | Apache Flink | AzureSenior-level Full TimeCupertino; Seattle18h ago
-
Applied Probability | Artificial Intelligence | C++ | Data Engineering | Data VisualizationExposure to senior leaders | Mentorship | Rotational projects | Technical trainingEntry-level Full Time141753-NC-Three Wells Fargo Center, Charlotte, United …18h ago
-
Senior Software Engineer - Storage Control Plane USD 266K-395KBlock Storage | C# | C++ | CI/CD | CephSenior-level Full TimeSan Francisco Office (Fremont St) R18h ago