[AI Research Div.] ML Serving Engineer (5년 이상)
Tasks
- Analyze latency and reliability issues
- Apply quantization for inference cost reduction
- Build monitoring logging alerting systems
- Design ML model serving architecture
- Implement CI CD and GitOps deployment
- Implement dynamic batching for LLM serving
- Operate real time LLM serving infrastructure
- Optimize KV cache efficiency
- Research inference acceleration and serving optimization
Perks/Benefits
- N/A
Skills/Tech-stack
Alerting | CI/CD | CUDA | Dynamic batching | GPU | GitOps | Inference Optimization | KV cache | LLM Inference | Language Models | Large Language Models | Logging | Machine Learning | Model Serving | Monitoring | Observability | PagedAttention | PyTorch | Quantization | TensorRT-LLM | VLLM
Education
N/A
Related jobs
-
Staff, Machine Learning Engineer [L6] (Search & Discovery) KRW 31080K-31080KAWS | Data Mining | Deep learning | Embeddings | ExperimentationSenior-level Full TimeSeoul, South Korea11h ago
-
Sr. Staff, Machine Learning Engineer [L7-1] (Search & Discovery) KRW 31080K-31080KAWS | Embedding Models | Experimentation | Feature Engineering | GCPSenior-level Full TimeSeoul, South Korea11h ago
-
Sr. Staff, Machine Learning Engineer (Search & Discovery) KRW 31000K-31000KDeep learning | Embeddings | Experimentation | Information Retrieval | JavaSenior-level Full TimeSeoul, South Korea11h ago
-
Staff, Machine Learning Engineer (Search & Discovery) KRW 31000K-31000KAWS | Data Analysis | Data Jobs | Deep learning | EmbeddingsSenior-level Full TimeSeoul, South Korea11h ago
-
Senior-level Full TimeSeoul, Korea R3d ago
-
Bias Evaluation | DPO | GPU Optimization | Inference Optimization | JAXSenior-level Full TimeSeoul, Korea R3d ago
-
Bias Mitigation | DPO | Data Pipelines | GPU Optimization | Inference architectureSenior-level Full TimeSeoul, Korea R3d ago
-
Computer Vision Engineer (Autonomous Driving) KRW 31000K-31000K3D Reconstruction | C++ | CUDA | Cloud Computing | Cloud processingSenior-level Full TimePangyo (Software Dream Center), South Korea R4d ago
-
Alerting | Data Pipelines | Distributed Systems | GPU infrastructure | InferenceMid-level Full TimeSeoul, Korea R7d ago
-
API Integration | Agentic Workflows | Context engineering | Distributed Systems | EvaluationMid-level Full TimeSeoul, Korea R7d ago
-
Batching | C++ | CUDA | Deep learning | Distributed SystemsSenior-level Full TimeSeoul HQ8d ago
-
Senior/Staff Applied Scientist (시니어/스태프 응용 과학자) KRW 65000K-90000KApache Spark | Attribution Modeling | Causal Inference | Causal reasoning | Experiment designSenior-level Full TimeSeoul, Korea8d ago
-
Data Engineer KRW 65000K-90000KAccess Control | Airflow | Apache Flink | Apache Spark | Argo WorkflowsSenior-level Full TimeSeoul,Seoul,Korea, Republic Of8d ago
-
Metrology Algorithm Developer for R&D TCT Korea KRW 48000K-67000KC# | Computer Vision | Deep learning | Image Processing | Image SegmentationEntry-level Full TimeHwaseong-Lucestar,KOR, Korea, Republic of8d ago
-
Staff Software Engineer, Machine Learning KRW 65000K-90000KBig Data | Causal Inference | Deep Neural Networks | Deep learning | JavaHybrid work | In office collaboration three times per weekSenior-level Full TimeSeoul, South Korea10d ago
-
[AI Research Div.] AI Agent Engineer (2년 이상) KRW 31000K-31000KAgentic AI | Benchmarking | Deep learning | Evaluation | LLM AgentsSenior-level Full TimeSeoul12d ago
-
Generative AI Systems Developer KRW 31000K-31000KAI Agents | AIOps | Azure | Backend Development | Cloud ArchitectureSenior-level Full TimeKR-AIA Tower, Korea, Republic of12d ago
-
[AI Research Div.] Research Engineer - Vision Language Action Game Agent (2년 이상 / 인턴) KRW 31000K-31000KData Preprocessing | Data pipeline | Deep learning | Experiment design | Inference OptimizationEntry-level Full TimeSeoul13d ago
-
Machine Learning Engineer (Match Group AI) KRW 31000K-31000KA/B | A/B Testing | B testing | Causal Inference | Causal analysisSenior-level Full TimeSeoul, South Korea13d ago
-
Autoscaling | Batching | Capacity Planning | Disaggregated Prefill | Disaggregated prefill decodeConference allowance | English education program | Equipment stipend | Flu vaccination support | Global buddy programSenior-level Full TimeSeoul, South Korea14d ago
-
Software Engineer II - Moloco Commerce Media KRW 50000K-67271KAPIs | Algorithms | Apache Beam | Apache Spark | BigQueryMid-level Full TimeSeoul, Korea14d ago
-
Machine Learning Engineer (Match Group AI) KRW 30000K-30000KA/B | A/B Testing | AWS | B testing | Causal InferenceMid-level Full TimeSeoul, South Korea14d ago
-
Software Engineer, Machine Learning - ML 인프라 KRW 31000K-31000KAI Agent | Experiment automation | LLM | Machine Learning | Machine Learning PipelineSenior-level Full TimeSEOUL15d ago
-
Software Engineer, Machine Learning KRW 31000K-31000KA/B | A/B Testing | Automated bidding | B testing | BigQueryMid-level Full TimeSEOUL15d ago
-
Software Engineer, Machine Learning - 검색 (품질) KRW 31000K-31000KA/B | A/B Testing | B testing | Deep learning | Graph AlgorithmsSenior-level Full TimeSEOUL15d ago