Inference Systems Backend Engineer - ARK Large Model Platform (Singapore)
Tasks
- Apply model quantization
- Build distributed LLM inference systems
- Collaborate with algorithm teams to optimize algorithms and systems
- Design large model training and inference architectures
- Develop large model training and inference systems
- Ensure high concurrency reliability and scalability
- Implement elastic scheduling
- Implement subgraph matching
- Improve compute utilization in distributed GPU clusters
- Integrate heterogeneous hardware with ML frameworks
- Manage GPU oversubscription
- Optimize model computation performance
- Orchestrate tasks
- Perform compiler optimization for models
- Schedule large scale inference traffic
- Tune large GPU training clusters
Perks/Benefits
- N/A
Skills/Tech-stack
C# | C++ | CUDA | CUDNN | Compilers | Computer Systems | Distributed Systems | GPU Performance | GPU Performance Optimization | Language Models | Large Language Models | Linux | MXNet | Megatron-LM | Model Quantization | Parallel Computing | Performance optimization | PyTorch | Python | SGLang | TensorFlow | TensorRT-LLM | VLLM
Education
Related jobs
-
Machine Learning Engineer - Global Payment - Singapore SGD 159K-240KApache Hive | Apache Spark | Deep learning | Java | Machine LearningSenior-level Full TimeSingapore, Singapore6h ago
-
Alerting | Automated rollback | C++ | CI/CD | Canary DeploymentSenior-level Full TimeSingapore, Singapore6h ago
-
C++ developer - Analytical Database SGD 153K-199KAlgorithms | C# | C++ | ClickHouse | Data StructuresSenior-level Full TimeSingapore, Singapore6h ago
-
A/B | A/B Testing | Autonomous Agents | B testing | Data MiningMid-level Full TimeSingapore, Singapore6h ago
-
Algorithm Engineer Graduate (Global E-Commerce, Supply Chain and Logistics) - 2026 Start (PhD) SGD 84K-91KDeep learning | Java | Knowledge graphs | LLM | Language ProcessingEntry-level Full TimeSingapore, Singapore6h ago
-
Machine Learning Engineer Graduate (Global E-Commerce, Risk Control) - 2026 Start (PhD) SGD 84K-108KData pipeline | Fraud Detection | Machine Learning | PyTorch | PythonEntry-level Full TimeSingapore, Singapore6h ago
-
Apache Flink | Apache FlinkDataStream | Apache HBase | Apache Spark | Apache YARNMid-level Full TimeSingapore, Singapore6h ago
-
C plus plus | CPU cache | CPU cache optimization | Cache optimization | GoSenior-level Full TimeSingapore, Singapore6h ago
-
Click Through Rate | Click Through Rate Prediction | Conversion Rate | Conversion Rate Prediction | Deep learningSenior-level Full TimeSingapore, Singapore6h ago
-
Algorithms | CTR Prediction | CVR Prediction | Data Structures | Deep learningSenior-level Full TimeSingapore, Singapore6h ago
-
C++ | Fine Tuning | Graph Algorithms | Human Feedback | Inference OptimizationSenior-level Full TimeSingapore, Singapore6h ago
-
Agent Frameworks | Algorithms | C plus plus | Data Structures | Fine TuningMid-level Full TimeSingapore, Singapore6h ago
-
Batch Processing | C# | C++ | Data Architecture | Distributed ConsensusMid-level Full TimeSingapore, Singapore6h ago
-
Batch Processing | C++ | Columnar Storage | Data Warehousing | DeltaLakeMid-level Full TimeSingapore, Singapore6h ago
-
Machine Learning Engineer - Search Ranking SGD 120K-199KAlgorithms | C++ | Computer Vision | Data Structures | Generative ModelsSenior-level Full TimeSingapore, Singapore6h ago
-
Machine Learning Engineer - Search (NLP) - Singapore SGD 70K-108KComputer Vision | Data Structures | Data Structures and Algorithms | Deep learning | Distributed SystemsMid-level Full TimeSingapore, Singapore6h ago
-
Machine Learning Engineer - Vertical Search SGD 164K-282KAlgorithms | C++ | Data Structures | Information Retrieval | JavaEntry-level Full TimeSingapore, Singapore6h ago
-
Software Engineer in Machine Learning Infra, Recommendation Architecture (ByteDance Singapore) SGD 122K-207KC++ | CUDA | CUDNN | Data Processing | DebuggingSenior-level Full TimeSingapore, Singapore6h ago
-
Software Engineer in Machine Learning Infra - Recommendation Architecture (ByteDance Singapore) SGD 122K-207KC++ | CUDA | CUDNN | Computer Architecture | Data ProcessingSenior-level Full TimeSingapore, Singapore6h ago
-
Apache Spark | C++ | Data Mining | Data Modeling | Data VisualizationSenior-level Full TimeSingapore, Singapore6h ago
-
C++ | Data Mining | Data Modeling | Data Warehousing | Distributed SystemsSenior-level Full TimeSingapore, Singapore6h ago
-
Apache Kafka | Apache Spark | C++ | Data Mining | Data ModelingSenior-level Full TimeSingapore, Singapore6h ago
-
C++ | Data Mining | Data Modeling | Elasticsearch | FlinkSenior-level Full TimeSingapore, Singapore6h ago
-
Backend Engineer, Large Model Knowledge System/Content understanding/RAG (ByteDance Singapore) SGD 149K-225KC++ | CUDA | Concurrency systems | Go | High PerformanceEntry-level Full TimeSingapore, Singapore6h ago
-
Backend Engineer - Large Model Knowledge System/Content understanding/RAG (ByteDance Singapore) SGD 123K-145KBilling | C++ | CUDA | Cloud Computing | Database systemsMid-level Full TimeSingapore, Singapore6h ago