Senior Software Engineer, Deep Learning Inference
Tasks
- Build production software in open source libraries
- Implement and optimize LLM inference algorithms
- Optimize fused MoE and quantized GEMM operators
- Own optimization features end to end
- Profile inference pipelines
- Solve distributed inference problems
- Write and tune GPU kernels
Perks/Benefits
- N/A
Skills/Tech-stack
C++ | CUDA | CUDA profiling | Collective communication | Communication Compute Overlap | Deep learning | Distributed Computing | FP8 | GPU kernel optimization | Kernel optimization | Mamba | Memory hierarchy | Mixed Precision | Mixture of Experts | Multi-node | Multi-node deployment | Networking | Node deployment | Nsight | Pipeline parallelism | PyTorch | Python | Quantization | Roofline model | State Space Models | State-Space | Tensor Parallelism | Transformers | Triton
Education
Related jobs
-
API Integration | Automation | Data Modeling | Indexing | JSONCollaborative fast-paced culture | Flexible work location | Fully remote | High-ownership environmentSenior-level Full TimeIsrael R6d ago
-
Actor-critic | Artificial Intelligence | Computational Efficiency | Computer Vision | Exploration/exploitationCareer growth opportunities | Continuous learning | Flexible work culture | Fully remote | International collaborationMid-level Full TimeIsrael R6d ago
-
APIs | Anomaly Detection | Data Modeling | Data Pipelines | DockerCareer growth opportunities | Flexible work environment | Remote workMid-level Full TimeIsrael R7d ago
-
Accelerator | Deep learning | Diffusers | EEG | Experiment designAutonomy and ownership | Career growth opportunities | Continuous learning culture | Flexible globally distributed work environment | Fully remote workMid-level Full TimeIsrael R7d ago
-
Computational optimization | Data Curation | Deep learning | Distributed Training | GPU TrainingCollaborative global culture | Flexible work location | Fully remote | High performance GPU access | Professional growth opportunitiesSenior-level Full TimeIsrael R8d ago
-
API Development | Argo CD | Argo Workflows | Cilium | GitOpsFull-time remote workMid-level Full TimeTel Aviv-Yafo, Tel Aviv District, IL R8d ago
-
Senior Designated Support Engineer GBP 67K-89KActive Directory | Erasure Coding | Ethernet | FTP | InfinibandFlexible hours | Remote work | Rotating on-call scheduleSenior-level Full TimeFrance, UK, Italy, Poland, Israel, Germany R16d ago
-
API Integration | AWS | Access Control | Apache Airflow | AuthenticationFlexible work schedule | Hybrid work model | Remote work flexibilityMid-level Full TimeIsrael - Raanana R21d ago
-
API Authentication | API pagination | API rate-limiting | AWS | Apache AirflowCareer growth opportunities | Collaborative work environment | Flexible schedule | Hybrid work model | Remote work optionMid-level Full TimeIsrael - Raanana R22d ago
-
AI Algorithms Team Lead ILS 341K-443KAlgorithm Development | Data Modeling | Deep learning | Documentation | Language ProcessingCollaborative culture | Employee gym | Free meals | Hybrid work model | Meal cardSenior-level Full TimeTel Aviv-Yafo, Tel Aviv District, IL R28d ago
-
Senior AI Solution Engineer ILS 341K-443KAI Model Evaluation | AI model | Amazon Athena | Apache Airflow | CI/CDGym membership | Healthy Meals | Hybrid work model | Meal card | ParkingSenior-level Full TimeTel Aviv-Yafo, Tel Aviv District, IL R28d ago
-
AWS | Azure | Distributed Systems | Django | ELKFlexible working | Hybrid work | Work from home optionSenior-level Full TimeIsrael R28d ago
-
Sr. Data Engineer - Cloud Security (Hybrid, ISR) ILS 380K-473KAWS | Apache Iceberg | Apache Spark | Cassandra | DockerCompetitive vacation and holidays | Employee networks | Paid adoption leave | Paid parental leave | Professional development opportunitiesSenior-level Full TimeTel Aviv (Sky Tower), Israel R1mo ago
-
AWS | Azure | Cloud deployment | Containerization | CrewAIRemote workMid-level Full TimeTel Aviv; Haifa R1mo ago
-
Senior AI Researcher - Applied Models ILS 420K-504KData Validation | Data benchmarking | DataOps | Experimental Design | Large-scaleCollaborative work environment | Hybrid work modelSenior-level Full TimeRamat Gan, Tel Aviv District, IL R1mo ago
-
Mid-level Full TimeIsrael R1mo ago
-
BLE | Bluetooth | C# | C++ | Communication ProtocolsHybrid work model | Work from home optionMid-level Full TimeRa'anana, Ha'sharon, IL R1mo ago
-
Agentic AI | Audio Processing | Computer Vision | Deep learning | Generative AISenior-level Full TimeRamat Gan (Hybrid) R1mo ago
-
Bit Error Rate Tester | Bit error rate | C# | C++ | CXLMid-level Full TimeHome Office, ISR, Israel R1mo ago