LLM Engineer (Reinforcement Learning)
Tasks
- Design self refine training structure
- Develop foundation models integrated with external knowledge and APIs
- Enhance generation accuracy and stability
- Improve LLM training efficiency
- Optimize direct alignment training with PPO GRPO DPO
- Prevent reward hacking
- Train models that select external tools based on instruction types
Perks/Benefits
- N/A
Skills/Tech-stack
DDP | Deep learning | Direct Preference Optimization | Distributed Training | Docker | Fine Tuning | GPU Computing | Horovod | Kubernetes | Language Processing | Natural Language | Natural Language Processing | Parameter efficient fine-tuning | Policy Optimization | Preference optimization | Proximal Policy Optimization | PyTorch | Python | Reinforcement Learning | Slurm | Supervised Fine Tuning
Education
Related jobs
-
A/B | A/B Testing | AWS | B testing | Data ValidationSenior-level Full TimeSeoul, South Korea7h ago
-
Staff, Machine Learning Engineer - Coupang Play KRW 25272K-26000KA/B | A/B Testing | AWS | B testing | Deep learningSenior-level Full TimeSeoul, South Korea22h ago
-
Artificial Intelligence | C++ | Data Modeling | Data Quality | Data pipelineMid-level Full TimeSeoul - 100 Hangang-daero, Korea, Republic …1d ago
-
Data Curation | Deep learning | Distributed Training | End to End | End-to-end trainingConference budget | Equipment stipend | Health checkup | Hybrid work | Learning budgetSenior-level Full TimeSeoul, South Korea2d ago
-
3D Computer Vision | Active Learning | Auto-labeling | BEV | C++Senior-level Full TimeKorea, Seoul, Korea, Republic of5d ago
-
Solutions Architect KRW 65000K-90000KApache Spark | Big Data | Cloud Platforms | Java | Proof of ConceptSenior-level Full TimeSeoul, South Korea6d ago
-
API Integration | Automation | BigQuery | Data Architecture | Data LakeSenior-level ContractSeoul, South Korea7d ago
-
API Integration | Anthropic | Apache Spark | Artificial Intelligence | Backend DevelopmentSenior-level Full TimeSeoul, South Korea7d ago
-
Bash | Data Processing | Docker | GCP | Infrastructure as CodeMid-level Full TimeIncheon, South Korea8d ago
-
ALSA | Android Audio | Android Audio Framework | Audio Framework | C#Senior-level Full TimeKorea, Seoul, Gangnam-gu, Korea, Republic of13d ago
-
Bash | Data Ingestion | Data Pipelines | Data Processing | DockerAsynchronous culture | Laid-back atmosphere | Remote-friendly team | Supportive leadershipMid-level Full TimeBusan, South Korea14d ago
-
Senior-level Full TimePangyo (Software Dream Center), South Korea16d ago
-
API Design | Algorithms | Apache Beam | Apache Spark | BigQueryMid-level Full TimeSeoul, Korea20d ago
-
Senior Software Engineer - Ads Experience (시니어 소프트웨어 엔지니어) KRW 65000K-90000KAPIs | Apache Beam | Apache Spark | BigQuery | BigtableSenior-level Full TimeSeoul, Korea20d ago
-
Bash | Cloud platform | Data Ingestion | Data Processing | DockerAsynchronous culture | Friendly work environment | Remote-friendlyMid-level Full TimeSeoul, South Korea20d ago
-
ARINC 429 | ARINC 664 | ARM | Agile | BashRelocation assistance not includedSenior-level Full TimeKOR - Seoul, South Korea, Korea, …21d ago
-
Senior-level Full TimeKOR - Seoul, South Korea, Korea, …21d ago
-
Senior-level Full TimePangyo (Software Dream Center), South Korea22d ago
-
Senior-level Full TimePangyo (Software Dream Center), South Korea22d ago
-
3D Vision | C++ | CMake | CNN | CUDADaily meal support | Flexible work hours | Hybrid work | No dress code | Paid sick leaveEntry-level Full TimeSeoul, Korea22d ago
-
C++ | Data Modeling | Data Quality | Data integration | Data pipelineMid-level Full TimeSeoul - 92, Hangang-daero, Korea, Republic …22d ago
-
Apache Flink | Apache Spark | Caching | Cloud deployment | DockerSenior-level Full TimeSeoul, Seoul, Korea, Republic of26d ago
-
AI Inference | Algorithms | C# | C++ | Computer ArchitectureHybrid work model | In-office collaboration | Remote work flexibilityMid-level Full TimeKOR - Seoul, Korea, Republic of27d ago
-
3D Deep Learning | 3D Mesh | API Development | C++ | Computer GraphicsBook Reimbursement | Flexible work schedule | Health checkup | Insurance benefits | Meal supportEntry-level Full TimeSeoul28d ago
-
Senior-level Full TimeCLOSED-Korea, Seoul, Daechi-dong, Korea, Republic of28d ago