Software Engineer, LLM Compilation
Tasks
- Debug performance issues with hardware team
- Implement FP8 quantization for FP16 models
- Implement drop in compatibility for transformer models
- Implement host CPU and accelerator synchronization
- Implement model parallelism and normalization components
- Integrate with vLLM and HuggingFace Transformers
- Optimize transformer attention kernels
Perks/Benefits
Skills/Tech-stack
Attention | C++ | CUDA | FP16 | FP8 | Hugging Face | Hugging Face Transformers | Machine Learning | Model Parallelism | Normalization | Quantization | VLLM
Education
N/A
Roles
Regions
Countries
States
Cities
Related jobs
-
Machine Learning Engineer, TikTok BRIC Account Security USD 145K-250KBehavioral analytics | Correlation Analysis | Data Warehousing | Data correlation | Data correlation analysisEntry-level Full TimeSan Jose, California, United States8h ago
-
Agent systems | C++ | Computer Vision | Data Processing | DebuggingSenior-level Full TimeSunnyvale, CA, USA9h ago
-
Software Engineer III, Generative AI, Payments Risk USD 147K-211KAgent systems | Big Data | Computer Vision | Data Processing | Data StructuresSenior-level Full TimeMountain View, CA, USA9h ago
-
Senior Software Engineer, Google Cloud Storage USD 174K-252KAs-a-Service | C++ | Chaos Engineering | Cloud Functions | Cloud StorageSenior-level Full TimeRaleigh, NC, USA; Durham, NC, USA9h ago
-
Robotics Software Engineer – Robot Integrations USD 70K-300KC++ | Computer Vision | Control Systems | Linux | Operating SystemHybrid or remote optionMid-level Full TimeIrvine, CA18h ago
-
Applied AI/ML - Senior Associate USD 175K-210KAgentic AI | Amazon Bedrock | Amazon SageMaker | Cloud deployment | ContainerizationBackup childcare | Financial coaching | Health care coverage | Mental health support | On-site health and wellness centersSenior-level Full TimeJersey City, NJ, United States19h ago
-
Artificial Intelligence | Computer Vision | Docker | Kubernetes | Language ProcessingHybrid office first work model | Performance based bonus opportunity | Relocation considerationMid-level Full TimeChicago, Illinois, United States20h ago
-
Engineering Lead Analyst - VP USD 125K-188KAI Automation | AI coding | AI coding assistant | CI/CD | Cloud401k | Medical/Dental/Vision | Paid time offSenior-level Full Time6400 LAS COLINAS BLVD IRVING, United …20h ago
-
AI & GenAI Data Scientist - EUR- Director USD 155K-410KAI architecture | Algorithm Design | Cloud Computing | Data Modeling | Deep learning401k | Dental insurance | Health insurance | Paid Holidays | Paid vacationExecutive-level Full TimeNew York - 300 Madison Avenue, …20h ago
-
Sr Machine Learning Engineer, Compliance USD 223K-268KAnomaly Detection | Batch data | Batch data pipelines | CI/CD | Data PipelinesComprehensive healthcare | Education subsidy | Learning and development support | Meal allowance | Wellness allowanceSenior-level Full TimeSan Jose, California, United States1d ago
-
Director, Compliance Data Science & AI USD 313K-375KAnomaly Detection | Data Engineering | Graph analytics | LLM | MLOpsComprehensive healthcare | Education subsidy | L D programs | Meal allowances | Team building programsExecutive-level Full TimeSan Jose, California, United States1d ago
-
Deep learning | Diffusion Models | Distributed Training | Flow Models | Generative AIComprehensive benefits | Equity | Real time impact on productsMid-level Full TimePalo Alto, CA1d ago
-
Continuous batching | Jupyter | KV cache | Low Latency | Machine LearningDaily meals | Housing subsidy | Medical, dental & vision coverage | Relocation supportMid-level Full TimeCupertino, CA1d ago
-
C++ | CI/CD | Cloud Computing | Containerization | Infrastructure EngineeringMid-level Full TimeCupertino, CA1d ago
-
Bundle adjustment | C++ | Control Theory | Linear systems | Numerical OptimizationSenior-level Full TimeOrange County, CA1d ago
-
AWS | Cloud platform | Computer Vision | Data Engineering | Data labelingCustomer-facing opportunities | International relocation support | Published research culture | Startup environment | Support for EB visasMid-level Full TimeSan Francisco, CA1d ago
-
AY2024-2025 #6042 Research Faculty in AI/ML - O'Donnell Data Science and Research Computing Institute USD 88K-108KC plus plus | C# | CUDA | Deep learning | Generative AITechnical mentorshipEntry-level Full TimeDallas, TX1d ago
-
Data Scientist / Data Engineer (TS/SCI with Poly) USD 140K-180KBig Data | Machine Learning | Python | R401k | Employee discount program | Flexible work schedule | Health savings account | Medical, dental, and vision coverageMid-level Full TimeAnnapolis Junction, MD, US1d ago
-
Senior Data Engineer - Fort Gordon, Georgia (APOGEE) USD 99K-148KC# | Data Governance | Data integration | GPU Computing | Gensim401k matching | Dental insurance | Disability coverage | Health insurance | Life insuranceSenior-level Full TimeFt. Gordon, US-GA, US1d ago
-
Senior/Staff AI Engineer USD 160K-210K3D Perception | C++ | Computer Vision | Cross-modal alignment | Distributed Training401k retirement plan | Company-Paid Holidays | Paid time off | Parental leave | Premium healthcare benefitsSenior-level Full TimeEast Palo Alto, CA1d ago
-
Anomaly Detection | Apache Airflow | Apache Spark | CUDA | Computer VisionAccess to cutting-edge hardware | Conference attendance support | Flexible work arrangements | Professional development | Rapid prototyping environmentMid-level Full TimeFairfax, VA, United States1d ago
-
Data Management and Analytics Engineer USD 80K-149KApache Spark | Azure | Base SAS | Data Governance | Data Integration StudioConference attendance support | Hybrid work | Paid leave | Professional development | Tuition assistanceMid-level Full TimeFairfax, VA, United States1d ago
-
Embedded Systems & Robotics Engineer USD 90K-176K3D CAD | 3D Printing | AADL | Buildroot | C#Hybrid work | On-call support | Remote work primarilyMid-level Full TimeFairfax, VA, United States1d ago
-
Software Engineer in Data Science USD 150K-180KAPIs | AWS | Airflow | Continuous Delivery | Continuous integrationSenior-level Full TimeHouston, TX, United States1d ago
-
Senior DevOps / MLOps Engineer USD 150K-250KCI/CD | Cybersecurity | Data Version Control DVC | Data version control | Distributed TrainingCross-functional collaboration | Startup environmentSenior-level Full TimePalo Alto, CA1d ago