Machine Learning Engineer — Inference Optimization
Tasks
- Benchmark model performance across GPUs CPUs and cloud systems
- Build and maintain inference serving infrastructure and custom runtimes
- Implement quantization KV cache optimization and speculative decoding
- Improve reliability monitoring and observability for production workloads
- Optimize cost efficiency and scalability of ML infrastructure
- Optimize machine learning inference systems for latency throughput scalability and cost
- Productionize new model architectures and translate research results into systems
- Profile GPU and CPU inference bottlenecks including memory kernels batching and data flow
Perks/Benefits
Skills/Tech-stack
Attention Mechanisms | Batching | CUDA | Compute Graphs | Distributed Systems | GPU Performance | GPU performance tuning | KV cache | Kernel optimization | Low Latency | Low-Latency Services | Machine Learning | Memory Optimization | Neural Networks | ONNX Runtime | Performance Tuning | PyTorch | Quantization | ROCm | Speculative decoding | Streaming | TensorRT | Triton | VLLM
Education
N/A
Related jobs
-
Data pipeline | Deep learning | GPU | JAX | Latency optimizationCareer growth | Flexible working hours | Fully remote | High autonomy | Professional developmentSenior-level Full TimeSouth Africa R7h ago
-
Agile | Apache Kafka | Avro | CI/CD | Confluent PlatformCollaborate with global engineering teams | Continuous learning and professional development | Exposure to large-scale distributed systems | Flexible hybrid working model | Modern Agile development environmentSenior-level Full TimePretoria, South Africa20h ago
-
Machine Learning Engineer UAH 1377K-1549KData Preparation | GPU Computing | JAX | Machine Learning | Machine Learning EngineeringSenior-level Full TimeEurope22h ago
-
Axolotl | Data Curation | Data Preprocessing | Direct Preference Optimization | Distributed SystemsContinuous learning | Fully remote | Inclusive workplace | International team collaboration | Open source exposureMid-level Full TimeSouth Africa R1d ago
-
Entry-level Full TimeStellenbosch, ZA4d ago
-
Senior Specialist Machine Learning Engineer ZAR 700K-840KAWS EC2 | AWS IAM | AWS S3 | Access Control | Amazon CloudWatchMedical aid | Retirement benefits | Risk benefitsSenior-level Full TimeMidrand, ZA5d ago
-
Senior Machine Learning Engineer ZAR 745K-860KAWS SageMaker | AWS Sagemaker Endpoints | Agile | Amazon Web Services | Big DataBirthday leave | Confidential counselling | Financial guidance | Free parking | Legal supportSenior-level Full TimeSouth Africa5d ago
-
Senior Machine Learning Engineer ZAR 745K-860KAWS | Agile | Big Data | BigQuery | Cloud platformBirthday leave | Confidential counselling | Financial guidance | Free parking | Free subscription takealotMORESenior-level Full TimeSouth Africa5d ago
-
Apache Spark | Azure Data | Azure Data Factory | Azure Databricks | Azure EventMid-level ContractSandton, South Africa5d ago
-
Senior Data Scientist (Azure Data Engineering & MLOps) ZAR 900K-1200KApache Spark | Azure Data | Azure Data Factory | Azure Data Lake | Azure Data Lake StorageSenior-level Contract Full TimeCape Town, Western Cape, South Africa6d ago
-
Senior Data Scientist (Azure Data Engineering & MLOps) ZAR 900K-1200KAzure Data | Azure Data Factory | Azure Data Lake | Azure Data Lake Storage | Azure DatabricksSenior-level Contract Full TimeCape Town, Western Cape, South Africa6d ago
-
Agricultural Valuation | Asset pricing | Collateral valuation | Credit Risk | Credit Risk AnalysisMid-level Full TimeJohannesburg, South Africa7d ago
-
Azure Bot | Azure Bot Service | Azure Cognitive | Azure Cognitive Services | Azure Machine LearningMid-level Full TimeMidrand, South Africa8d ago
-
AI Engineering - Master Specialist ZAR 780K-920KApache Kafka | Apache Spark | C++ | CUDA | Cloud ComputingSenior-level Full TimeJohannesburg, ZA8d ago
-
Senior Data Engineer ZAR 1100K-1200KAPI | Apache Flink | Apache Spark | Apache Spark Streaming | Azure DataSenior-level Full TimeSouth Africa10d ago
-
Agricultural Valuation | Asset pricing | Collateral valuation | Credit Risk | Data ScienceMid-level ContractSandton, South Africa13d ago
-
Mid-level Full TimeBellville, South Africa17d ago
-
Airflow | Amazon Redshift | BigQuery | CI/CD | ChromaDBFlexible working hours | Remote workSenior-level Full TimeSouth Africa - Remote R18d ago
-
Senior-level Full TimeWC, South Africa19d ago
-
Senior-level Full TimeWC, South Africa19d ago
-
Senior Generative AI Engineer ZAR 603K-650KAI Governance | AI Security | AWS | Azure | Cloud PlatformsContinuous learning and development | Mentorship and team growthSenior-level Full TimeWC, South Africa19d ago
-
AI / Machine Learning Engineer ZAR 360K-440KCI/CD | Cloud Computing | Computer Vision | Data Governance | Data PipelinesMid-level Full TimeWC, South Africa19d ago
-
Senior RAG Engineer ZAR 450K-650KAPI Development | Chroma | Distributed Systems | Embeddings | Enterprise SearchSenior-level Full TimeWC, South Africa19d ago
-
Associate Staff Engineer (Graph Data Engineer) ZAR 464K-500KAKS | API Development | Access Control | Active Directory | AutoscalingMid-level Full TimeJohannesburg, South Africa19d ago
-
Senior Machine Learning Engineer ZAR 540K-720KAWS | AWS CodePipeline | Azure | CI/CD | Cloud platformSenior-level Full TimeBrackenfell, ZA20d ago