Intern - GenAI Benchmarking (MLE) / On-Device Model Deployment (SWE)
Seoul, Korea, Republic of
KRW 45000K-67000K (estimate) Entry-level Internship
Tasks
- Apply graph level changes for static shape export and KV cache allocation
- Build benchmarking frameworks for reproducible evaluation
- Define evaluation strategies and key performance metrics
- Develop reliable generative model evaluation methods
- Implement efficient inference techniques such as speculative decoding
- Implement long context handling and KV cache management
- Integrate and update Hugging Face Transformers components
- Maintain code for model decoding logic
- Replace operators with NPU DSP compatible equivalents
- Restructure model architectures for efficient on device inference
- Support post training quantization and mixed precision quantization
- Validate accuracy of quantized models against reference models
- Write tested documented code with automated testing and code review
Perks/Benefits
- N/A
Skills/Tech-stack
AIMet | Automated testing | Executorch | Git | Hugging Face | KV cache | Language Models | Large Language Models | Mixed Precision | ONNX Runtime | Post-training | Post-training Quantization | PyTorch | Python | Quantization | Speculative decoding | Static Shape Graph Export | Transformers
Education
Related jobs
-
Software Engineer II - Moloco Commerce Media KRW 50000K-67271KAPIs | Algorithms | Apache Beam | Apache Spark | BigQueryMid-level Full TimeSeoul, Korea9h ago
-
Machine Learning Engineer (Match Group AI) KRW 30000K-30000KA/B | A/B Testing | AWS | B testing | Causal InferenceMid-level Full TimeSeoul, South Korea10h ago
-
Bash | Cloud platform | Data Processing | Docker | Google CloudAsynchronous culture | Flexible, hands-off management | Friendly work environment | Industry impact | Remote-friendlyMid-level Full TimeBusan, South Korea1d ago
-
Anomaly Detection | Artificial Intelligence | Data Architecture | Edge Computing | Ethernet/IPMid-level Full TimeNonsan-si, Korea, Korea, Republic of1d ago
-
Intern- Deep Learning R&D for Automated Driving KRW 48000K-67000KC# | C++ | Deep learning | Machine Learning | PyTorchEntry-level InternshipSeoul, Korea, Republic of1d ago
-
Platform Engineer KRW 44000K-50000KAgent Orchestration | Agentic Workflows | Cloud infrastructure | Code repair | Context engineeringMid-level Full TimeSeoul, KR, 065784d ago
-
Sr. Lead Engineer (Full Stack Developer) KRW 65000K-90000KAWS | Azure | Client-Server | Client-Server Architecture | Data ModelingSenior-level Full TimeSeoul, Korea, republic of6d ago
-
Bash | Data Processing | Docker | GCP | LinuxMid-level Full TimeSeoul, South Korea6d ago
-
Senior-level Full TimeSeoul HQ7d ago
-
Machine Learning Software Engineer (Match Group AI) KRW 44000K-44000KApache Flink | Apache Kafka | Apache Spark | Batch Processing | C#Mid-level Full TimeSeoul, South Korea8d ago
-
Algorithms | Batch Processing | C# | Data Structures | Distributed SystemsMid-level Full TimeSeoul, South Korea8d ago
-
AI Engineer (Navigation Agent) KRW 30880K-30880KClassification | Data Quality | Dataset Construction | Deep learning | Distributed TrainingSenior-level Full TimePangyo (Software Dream Center), South Korea11d ago
-
AI Engineer (On-device Agent Orchestration 개발) KRW 31000K-31000KAndroid | C# | Generative AI | Java | KotlinSenior-level Full TimePangyo (Software Dream Center), South Korea13d ago
-
[집중채용] LLM Engineer (LLM Training) KRW 26800K-26800KDDP | Deep learning | Distributed Training | Docker | Efficient Fine TuningSenior-level Full TimePangyo (Software Dream Center), South Korea13d ago
-
LLM Engineer (Reinforcement Learning) KRW 26800K-26800KDDP | DPO | Deep learning | Distributed Training | DockerSenior-level Full TimePangyo (Software Dream Center), South Korea13d ago
-
[집중채용] Deep Learning Engineer (음성 인식 및 wake word detection 개발) KRW 30880K-30880KAndroid | Audio Processing | C# | C++ | CI/CDSenior-level Full TimePangyo (Software Dream Center), South Korea13d ago
-
Senior-level Full TimePangyo (Software Dream Center), South Korea13d ago
-
Senior Backend Engineer (Intelligence Data Platform) KRW 30880K-30880KAPI Development | AWS | Backend Services | Data Pipelines | Data QualitySenior-level Full TimePangyo (Software Dream Center), South Korea13d ago
-
Senior Data Engineer KRW 65000K-90000KAPI Gateway | AWS | AWS CDK | AWS CloudFormation | AWS LambdaSenior-level Full TimeSeongnam, Korea, Republic of14d ago
-
Physical AI Engineer (Model) KRW 31000K-31000KC++ | CUDA | Deep learning | Imitation Learning | JAXSenior-level Full TimePangyo (Software Dream Center), South Korea15d ago
-
Senior Physical AI Engineer (Simulation) KRW 31000K-31000K3D Gaussian Splatting | C++ | CARLA | CUDA | Closed LoopSenior-level Full TimePangyo (Software Dream Center), South Korea15d ago
-
Apache Airflow | Apache Hive | Apache Spark | Data Lakehouse | Data pipelineSenior-level Full TimePangyo (Software Dream Center), South Korea15d ago
-
Senior Computer Vision Engineer (Autonomous Driving) KRW 31000K-31000K3D Reconstruction | 3D shape modeling | C++ | CUDA | CameraSenior-level Full TimePangyo (Software Dream Center), South Korea15d ago
-
Senior AI Data Pipeline Engineer KRW 31000K-31000KApache Airflow | Apache Flink | Apache Kafka | Apache Spark | Cloud NativeSenior-level Full TimePangyo (Software Dream Center), South Korea15d ago
-
Senior Data Visualization Developer (Autonomous Driving) KRW 31000K-31000KAWS | Argo CD | CI/CD | Docker | FastAPISenior-level Full TimePangyo (Software Dream Center), South Korea15d ago