Machine Learning Engineer — Inference Optimization
Tasks
- Benchmark model performance across hardware environments
- Build and maintain inference serving infrastructure
- Contribute to scalable maintainable ML infrastructure
- Implement quantization and KV cache optimization
- Implement speculative decoding batching and streaming
- Improve reliability monitoring observability and cost efficiency
- Optimize machine learning inference systems for latency throughput and scalability
- Productionize machine learning model architectures with research teams
- Profile and identify GPU CPU inference bottlenecks
Perks/Benefits
Skills/Tech-stack
Attention Mechanisms | Batching | CUDA | Cache optimization | Compute Graphs | Distributed Systems | GPU Memory Optimization | GPU Performance | GPU Performance Optimization | GPU memory | KV cache | KV cache optimization | Language Models | Large Language Models | Low Latency | Low-Latency Systems | Machine Learning | Memory Optimization | Neural Networks | ONNX Runtime | Performance optimization | PyTorch | Quantization | ROCm | Speculative decoding | Streaming | TensorRT | Triton | VLLM
Education
N/A
Related jobs
-
AI Agents | AI Foundry | Azure AI | Azure AI Foundry | Azure DevOpsFlexible working hours | Hybrid working | International working environment | Knowledge sharing sessions | Learning opportunitiesEntry-level InternshipZurich, Switzerland R16h ago
-
APIs | Agent Development | Agent Development Kit | Agent systems | Computer VisionSenior-level Full TimeZürich, Switzerland20h ago
-
Access Transparency | Artificial Intelligence | C++ | Cloud APIs | Customer-managed encryption keysSenior-level Full TimeZürich, Switzerland20h ago
-
Software Engineer, Cloud AI Research, Co-Scientist CHF 122K-227KAgent systems | Agentic AI | Algorithms | C++ | Data AnalysisMid-level Full TimeZürich, Switzerland20h ago
-
Senior AI Engineer CHF 129K-192KBehavior analytics | Detection and Response | Fine Tuning | Langchain | Language ModelsAnnual training budget | Company events and workshops | Enhanced maternity leave | Enhanced paternity leave | Hybrid optionsSenior-level Full Timeremote or office, Zürich, Switzerland R20h ago
-
Cloud Computing | Code review | Data Modalities | Deep learning | DockerCollaborative & Inclusive Culture | Four-day work week | Fully remote work | Opportunity for open source contributions | Unlimited paid time offSenior-level Full TimeSwitzerland R23h ago
-
BF16 | Backpropagation | Checkpointing | Convergence | Data parallelismContinuous learning | Cutting-edge AI work | Equity opportunities | Experimentation culture | Fast feedback loopsMid-level Full TimeSwitzerland23h ago
-
Deep learning | Distributed Training | Experiment tracking | Inference Optimization | JAXAsync-first culture | Equity opportunities | High ownership | Remote-friendlySenior-level Full TimeSwitzerland23h ago
-
Senior AI Engineer / Technical Consultant CHF 128K-192KAPI Development | Amazon Web Services | Azure | CI/CD | Cloud platformSenior-level Full TimeLausanne, Vaud, Switzerland1d ago
-
Senior-level Full TimeLausanne, Vaud, Switzerland1d ago
-
API Integration | Change Management | Cloud Data | Cloud Data Warehouse | Data ContractsAutonomy | Collaborative team | Flexible working arrangements | Fully remote | High ownership roleSenior-level Full TimeSwitzerland R1d ago
-
Embedded Software Engineer (Camera & Driver Platform) CHF 102K-138KBash | C++ | Cross-compilation | Cross-debugging | DNSCar parking | Enhanced maternity and paternity leave | Flexible working hours | Generous holiday allowance | Hybrid workplaceMid-level Full TimeZurich, Switzerland2d ago
-
Senior Data Scientist CHF 128K-192KAWS | Apache Spark | Azure | Databricks | GitCross-functional teamwork | Customer contact | Professional development | Travel requiredSenior-level Full TimePully, Switzerland2d ago
-
API Design | Backend architecture | Command Line | Command-line interfaces | Database systemsCompany-provided equipment | Continuous learning allowance | Flexible working hours | Fully remote | Health insurance allowanceSenior-level Full TimeSwitzerland R3d ago
-
Senior AI Engineer CHF 128K-192KAgentic AI | Auditability | Cost Optimization | Evaluation Pipelines | ExperimentationOnsite work environmentSenior-level Full TimeZurich, Switzerland3d ago
-
A/B | A/B Testing | AWS | Azure | B testingFully remote work | Healthcare coverage | Paid parental leave | Relocation assistanceMid-level Full TimeSwitzerland R4d ago
-
Software Engineer - Embedded Software (d/f/m) CHF 95K-146KAI Inference | C# | C++ | Git | JavaAccident insurance | Defined contribution pension plan | Global employee benefits | Sick pay insurance | Wellbeing initiativesMid-level Full TimeCH-ZH-ZURICH-TECHNOPARK STRASSE 1, Switzerland4d ago
-
Robotics Software Engineer - Sim-to-Real CHF 115K-158KC++ | Embedded Systems | Physics simulation | PyTorch | PythonComprehensive benefits packageMid-level Full TimeSwitzerland, Zurich4d ago
-
Research Scientist/ Engineer - Special Projects CHF 134K-192K3D Reconstruction | Computer Graphics | Computer Vision | Deep learning | Image SynthesisSenior-level Full TimeZurich7d ago
-
AWS | Apache Airflow | Cloud platform | Deep learning | DockerAccess to modern development tools | Equity opportunities | Medical/Dental/Vision insurance | Unlimited paid time off | Work from homeMid-level Full TimeSwitzerland R7d ago
-
AWS | Apache Spark | Data Analysis | Hadoop | JavaRemote workSenior-level Full TimeZürich, Switzerland R7d ago
-
Senior ML Engineer (Zürich) CHF 140K-232KAdversarial Testing | Computer Vision | Data Generation | Data pipeline | Generative AISenior-level Full TimeZürich8d ago
-
Staff ML Engineer (Zürich) CHF 140K-232KComputer Vision | Data Modeling | Data collection | Language Processing | Machine LearningSenior-level Full TimeZürich8d ago
-
Senior Expert I/II, Data Science, Modeling & Simulation CHF 102K-189KComputational Biology | Data Analysis | Data Mining | Data Visualization | Deep learningFlexible working options | Global recognition programs | Hybrid working | Insurance plans | Paid parental leaveSenior-level Full TimeBasel (City), Switzerland8d ago
-
CUDA | Continuous Deployment | Continuous integration | Imitation Learning | JAXMid-level Full TimeSwitzerland, Zurich8d ago