Backend Inference Runtime Engineer Graduate (AML Inference) - 2027 Start
Tasks
- Apply operator fusion and compilation optimization
- Benchmark against TensorRT-LLM
- Benchmark against vLLM
- Design and develop distributed parallel inference solutions
- Enhance GPU NPU hardware adaptability
- Implement mixture of experts expert parallelism
- Implement pipeline parallelism
- Implement sequence parallelism
- Implement tensor parallelism
- Improve end to end GPU performance
- Iterate on inference performance and cost efficiency
- Optimize GPU memory access
- Optimize large model inference engine architecture
- Reduce cross card communication overhead
- Tune computing pipeline and asynchronous scheduling
Perks/Benefits
- N/A
Skills/Tech-stack
Asynchronous Scheduling | Benchmarking | Cache optimization | Compilation Optimization | Distributed Systems | GPU Computing | GPU Memory Optimization | GPU Performance | GPU Performance Optimization | GPU memory | High Performance | High-Performance Computing | Language Models | Large Language Models | Machine Learning | Memory Optimization | Mixture of Experts | NPU | Operator fusion | Performance Computing | Performance optimization | Pipeline parallelism | Sequence parallelism | Tensor Parallelism | TensorRT-LLM | VLLM
Education
Bachelor of Engineering | Bachelor of Science | Master of Science
Related jobs
-
Autonomous Agents | Data Modeling | Deep learning | Experimentation | Machine LearningMid-level Full TimeSingapore, Singapore4h ago
-
Alerting | Canary Deployment | Distributed Systems | High Availability | Machine LearningEntry-level Full TimeSingapore, Singapore4h ago
-
Bottleneck diagnosis | Code generation | Computation Scheduling | Distributed Systems | Graph optimizationEntry-level Full TimeSingapore, Singapore4h ago
-
Data Pipelines | Infrastructure Engineering | Machine Learning | Performance Analysis | PythonEntry-level Full TimeSingapore, Singapore4h ago
-
API Development | Deep learning | Distributed Systems | Fine Tuning | GPU ComputingEntry-level Full TimeSingapore, Singapore4h ago
-
Apache Flink | Data Processing | Data integration | Distributed Systems | Real TimeEntry-level InternshipSingapore, Singapore4h ago
-
APIs | Data Catalog | Data Governance | Data Security | Data integrationEntry-level InternshipSingapore, Singapore4h ago
-
Data Catalog | Data Governance | Data Security | Distributed Systems | JavaEntry-level Full TimeSingapore, Singapore4h ago
-
Agentic AI | Data Analysis | Fraud Detection | Language Models | Language ProcessingEntry-level Full TimeSingapore, Singapore4h ago
-
AI Agents | Data Mining | Fraud Detection | LLM | Language ProcessingEntry-level Full TimeSingapore, Singapore4h ago
-
Machine Learning Engineer Graduate (Global E-Commerce, Platform Governance) - 2027 Start (PhD) SGD 70K-70KData Modeling | Feature Engineering | Graph Databases | Graph Learning | Machine LearningEntry-level Full TimeSingapore, Singapore4h ago
-
Backend Development | CPU | Cloud Computing | Distributed Systems | GPUEntry-level Full TimeSingapore, Singapore4h ago
-
Computer Vision | Data Processing | Generative AI | Graph Neural Networks | Language ModelsEntry-level InternshipSingapore, Singapore4h ago
-
Feature Engineering | Fraud Detection | Graph Neural Networks | Language Models | Large Language ModelsMid-level Full TimeSingapore, Singapore4h ago
-
Senior Backend Engineer - AML Engine Orchestration SGD 170K-225KAuto Scaling | Distributed Systems | Embeddings | Fine Tuning | GPU TrainingSenior-level Full TimeSingapore, Singapore4h ago
-
Computer Vision | Generative AI | Information Retrieval | Language Processing | Machine LearningSenior-level Full TimeSingapore, Singapore4h ago
-
Computer Vision | Language Processing | Machine Learning | Multi-Modal | Multi-Modal LearningEntry-level Full TimeSingapore, Singapore4h ago
-
Backend Engineer , AML Engine Orchestration SGD 170K-225KAuto Scaling | Deep learning | Distributed Systems | Embeddings | Fine TuningSenior-level Full TimeSingapore, Singapore4h ago
-
Adaptive Frame Rate | Audio Processing | Computer Vision | Deep learning | Frame rateSenior-level Full TimeSingapore, Singapore4h ago
-
Apache Flink | Apache Hive | Apache Spark | Big Data | C#Entry-level Full TimeSingapore5h ago
-
Anomaly Detection | Apache Flink | Apache Spark | C++ | Computer VisionEntry-level Full TimeSingapore5h ago
-
Algorithms | Computer Vision | Data Structures | Deep learning | Hyperscale ModelingSenior-level Full TimeSingapore5h ago
-
Data center | Data center operations | Disaster Recovery | Distributed Systems | Machine LearningGlobal team collaboration | On-call rotationMid-level Full TimeSingapore, Singapore5h ago
-
API | Canary Deployment | Circuit Breaker | High Availability | Load BalancingMid-level Full TimeSingapore, Singapore5h ago
-
Partner Forward Deployed Engineer, GenAI, Google Cloud SGD 144K-250KAgent Development | Agent Development Kit | Agent Development Kit ADK | Agent systems | Cloud platformMid-level Full TimeSingapore6h ago