Senior Software Engineer, AI Inference Systems
Tasks
- Architect scheduling and orchestration for inference deployments
- Benchmark GPU kernels and inference
- Build kernel DSLs and compiler infrastructure
- Conduct and publish ML systems research
- Contribute features to vLLM
- Define MLPerf inference benchmarking tools
- Deploy containerized inference on GPU clusters
- Develop and optimize GPU kernels
- Profile and optimize inference framework
Perks/Benefits
Skills/Tech-stack
Algorithms | C++ | CI/CD | CUDA | CUDA Graphs | Cgroups | Computer Architecture | Cutlass | Data Structures | Deep learning | Distributed Systems | Docker | Infrastructure as Code | Kubernetes | LLVM | Linux | Linux Namespaces | MLIR | NCCL | Nsight Compute | Nsight Systems | Operating Systems | Parallel Programming | Production observability | Profiling | PyTorch | PyTorch Inductor | Python | SGLang | Slurm | Tensor cores | TorchDynamo | Triton | VLLM | XLA | “as-code”
Education
Related jobs
-
Senior Machine Learning Engineer (all genders) EUR 53K-66KAWS | Agile | Airflow | Amazon SageMaker | Apache FlinkDiscounts | Employee shares program | Health and wellbeing support | Hybrid work | Mental health supportSenior-level Full TimeBerlin, Germany R1d ago
-
Mid-level Full TimeGermany, Berlin - Remote R1d ago
-
Apache Flink | Apache Kafka | Apache Spark | Data Governance | Data ModelingAdditional paid leave | Employee stock options | Opportunity to work remotely while traveling | Paid volunteering opportunities | Performance bonusesSenior-level Full TimeGermany R1d ago
-
(Senior) AI Engineer (all genders) EUR 65K-80KCloud Platforms | Containerization | DevOps | Docker | Machine Learning30 days vacation | Bike program | Company fitness | E-learning support | International clientsMid-level Full TimeBremen, Munich, Mannheim, Mainz, Berlin, Remote R1d ago
-
Chatbot LLM Engineer (all genders) EUR 38K-66KAgile | Language Models | Language Processing | Large Language Models | Natural Language30 days vacation | Bio fruits and vegetables | E-learning support | Family-friendly workplace | Fitness benefitsMid-level Full TimeBremen, Munich, Mannheim, Mainz, Berlin, Remote R1d ago
-
AI Engineer (m/w/d) EUR 53K-53KAI Services | Azure | Azure AI | Azure AI Services | Azure Machine Learning100 percent homeoffice | 30 vacation days | Company car | Flexible working hours | JobradSenior-level Full TimeHome-Office / Deutschlandweit, München, Gütersloh R1d ago
-
C# | Electromagnetism | MATLAB | Mechanics | NumPyFlexible part-time schedule | Freelance project-based workEntry-level FreelanceGermany - Remote R2d ago
-
Electromagnetism | Mathematical Modeling | Mechanics | NumPy | Numerical SimulationFlexible weekly hours | Freelance project assignments | Part-time project-based workSenior-level FreelanceGermany - Remote R2d ago
-
Computational physics | Data Validation | Electromagnetism | Mechanics | NumPyPart time freelance projectsEntry-level FreelanceGermany - Remote R2d ago
-
AWS CDK | AWS Lambda | AWS SageMaker | Amazon S3 | Apache IcebergDog-friendly offices | Flexible working hours | Home-office allowance | Hybrid work setup | Learning daysEntry-level Part TimeBerlin, Germany; Hamburg, Germany R2d ago
-
API | Automation | Code platforms | Language Models | Large Language ModelsFully remote | High autonomy | Learning opportunities | Location flexibilityMid-level Full TimeGermany R2d ago
-
Consultant SAP Data & Analytics EUR 60K-75KBusiness Technology Platform | Data Flows | Data Intelligence | Data Modeling | Data VisualizationCompany pension | EGYM Wellpass | Flexible work hours | Health programs | JobradMid-level Full TimeHamburg, München, Mannheim, Remote, Dortmund R2d ago
-
AI Services | Anthropic API | Automated testing | Azure AI | Azure AI ServicesCertification opportunities | Collaborative team | Continuous learning | Cross-industry projects | Flexible work arrangementsSenior-level Full TimeBerlin, Germany R3d ago
-
Senior Data Engineer (Modern Data Platform & AI) (all genders) | Berlin, hybrid or remote EUR 68K-90KAWS | Airflow | Amazon Athena | Amazon S3 | Apache SparkDiscounted BVG ticket | Hybrid work | Jobrad | Mental health support | Remote work optionSenior-level Full TimeGermany - Remote R3d ago
-
Bilby | CAMB | Class | Computational physics | DOLFINxSenior-level FreelanceGermany - Remote R4d ago
-
Combinatorics | Graph theory | MATLAB | NumPy | Number theoryFlexible hours | Freelance opportunities | Part-time projects | Project based workSenior-level FreelanceGermany - Remote R5d ago
-
AWS | CI/CD | CUDA | DDP | DeepSpeedAnnual paid leave | Career growth opportunities | High-ownership environment | Hybrid office access | Public holidaysSenior-level Full TimeGermany R5d ago
-
Deep learning | Langchain | MLOps | Model Deployment | NumPyEnglish language required | Freelance projects | Part-time work | Project-based assignmentsMid-level FreelanceGermany - Remote R6d ago
-
Freelance Machine Learning Engineer USD 116KLangchain | MLOps | NumPy | Pandas | Prompt engineeringPart-time schedule | Project based workMid-level FreelanceGermany - Remote R6d ago
-
Data Engineer GBP 57K-75KAirflow | Apache Spark | Dagster | Data Governance | Data ModelingCareer growth and learning opportunities | Collaborative and innovative culture | Flexibility | International environment | Opportunity to work on impactful AI projectsMid-level Full TimeGermany; Israel; Netherlands; Prague, Czech Republic; … R6d ago
-
Dozent (w/m/d) für AI und Big Data - 100% Remote EUR 34K-46KArtificial Intelligence | Cloud Computing | Curriculum Development | Data Ethics | Data PrivacyCorporate discounts | Health and wellness benefits | Paid time off | Professional development support | Remote workMid-level Full Time100% Remote in Deutschland R7d ago
-
Senior Data Engineer (m/w/d) EUR 60K-84KAWS | Apache Hudi | Apache Iceberg | Azure | CI/CDCoaching | Corporate benefits | Deutschlandticket subsidy | Fitness facilities | Flexible working hoursMid-level Full TimeHybrid, München, Frankfurt, Berlin, Leipzig, Essen, … R7d ago
-
Staff AI Engineer EUR 65K-85KAB Testing | Agentic Systems | Artificial Intelligence | Backend Development | DeploymentBVG ticket | Dog-friendly office | Flexible hours | Hybrid work setup | Independent workSenior-level Full TimeBerlin R7d ago
-
Data Engineer (m/f/d) EUR 60K-75KAWS | Argo Workflows | Axios | Django | FastAPIDevelopment budget | Direct customer exposure | Equipment support | Hybrid work up to 2 days remote | Mac providedMid-level Full TimeBerlin, Berlin, Germany R8d ago
-
AI Agents | Integration | JavaScript | Langchain | Language ModelsAI program allowance | Company-provided laptop | Continuous learning and career development | Dental insurance | Family focused programsSenior-level Full TimeGermany R8d ago