Senior Applied Scientist, Reinforcement Learning
Tasks
- Automate post training loops with agents
- Build reward models
- Build verifiers
- Collaborate with research engineering and clinical teams
- Design on policy distillation post training methods
- Design reinforcement learning post training methods
- Develop conversational ai environments for healthcare rl training
- Run experiments to measure post training gains
- Run llm as judge evaluation pipelines
Perks/Benefits
- N/A
Skills/Tech-stack
Agent automation | Human Feedback | LLM Training | LLM-as-judge | Language Processing | Learning from Human Feedback | Natural Language | Natural Language Processing | On Policy | On policy Distillation | Policy Distillation | PyTorch | Python | RLHF | Reinforcement Learning | Reinforcement Learning from Human Feedback | Reward Modeling | Reward Verifier | Synthetic data
Education
Regions
Countries
States
Cities
Related jobs
-
Featured Feat. Principal Knowledge & Data Architect USD 174K-284KAWS Neptune | Canonicalization | Chunking | Cypher | DBTBenefits including health and wellness programs | Health, wellness, and retirement plansSenior-level Full TimeHeadquarters - Chevy Chase, MD R19d ago
-
Senior Data & ML Ops Engineer USD 137K-206KAWS | Airflow | Amazon SageMaker | Automated retraining | Automated testingHealth insurance | Paid time off | Retirement contributionsSenior-level Full TimeBoston, Massachusetts, US, 022104h ago
-
Bash | Cloud platform | Data Processing | Docker | Google CloudAsynchronous culture | Flexible remote work | Laid-back atmosphereMid-level Full TimeSeattle, WA, USA6h ago
-
Bash | Cloud infrastructure | Cloud platform | Data Ingestion | Data ProcessingAsynchronous culture | Diverse and inclusive workplace | Portfolio support | Remote-friendly environmentMid-level Full TimeChicago, IL, USA6h ago
-
Bash | Cloud platform | Data Ingestion | Data Processing | DockerAsynchronous work culture | Career growth | Competitive compensation | Remote-friendly cultureMid-level Full TimeLong Beach, CA, USA6h ago
-
Bash | Data Processing | Docker | GCP | Large Scale DataAsynchronous culture | Friendly work environment | Remote workMid-level Full TimeSalt Lake City, UT, USA6h ago
-
Bash | Cloud platform | Data Processing | Docker | Google CloudAsynchronous work culture | Flexible management approachMid-level Full TimeMountain View, CA, USA6h ago
-
Bash | Cloud platform | Data Processing | Docker | Google CloudAsynchronous culture | Laid-back atmosphere | Remote workMid-level Full TimeSunnyvale, CA, USA6h ago
-
AI Data | Bash | Cloud infrastructure | Data Ingestion | Data Ingestion PipelinesAsynchronous culture | Flexible team environment | Remote-friendlyMid-level Full TimeBerkeley, CA, USA6h ago
-
Bash | Cloud platform | Data Processing | Docker | Google CloudAsynchronous culture | Collaborative team environment | Flexible, hands-off management | Remote-friendly work environmentMid-level Full TimeFremont, CA, USA6h ago
-
Bash | Cloud platform | Data Processing | Docker | Google CloudAsynchronous culture | Laid back environment | Remote-friendlyMid-level Full TimeSanta Monica, CA, USA6h ago
-
Bash | Data Processing | Docker | GCP | Large Scale DataAsynchronous work culture | Career growth | Flexible management | Impactful missionMid-level Full TimeIrvine, CA, USA6h ago
-
Bash | Data Ingestion | Data Processing | Docker | GCPAsynchronous culture | Flexible management approach | Remote/distributed work | Supportive teamMid-level Full TimeHuntsville, AL, USA6h ago
-
Bash | Data Processing | Docker | GCP | Infrastructure as CodeAsynchronous work culture | Friendly work environment | Remote-first environmentMid-level Full TimeTampa, FL, USA6h ago
-
Bash | Cloud platform | Data Processing | Docker | Google CloudAsynchronous culture | Bonus | Equity | Friendly work environment | Portfolio supportMid-level Full TimeNewark, NJ, USA6h ago
-
Bash | Cloud platform | Data Processing | Data Processing Pipelines | Dataset EngineeringMid-level Full TimePhiladelphia, PA, USA6h ago
-
Bash | Data Processing | Docker | GCP | Infrastructure as CodeAsynchronous work culture | Friendly work environment | Portfolio supportMid-level Full TimeNew Haven, CT, USA6h ago
-
Bash | Cloud platform | Data Processing | Docker | Google CloudAsynchronous culture | Entrepreneurial team | Friendly laid-back atmosphere | Portfolio and LinkedIn sharing | Remote friendly distributed settingMid-level Full TimeTacoma, WA, USA6h ago
-
Bash | Cloud platform | Data Ingestion | Data Processing | DockerAsynchronous culture | Flexible work environment | Impactful product mission | Remote workMid-level Full TimeColorado Springs, CO, USA6h ago
-
Bash | Data Processing | Data Processing Pipelines | Docker | GCPAsynchronous culture | Bonus | Equity | Flexible management | Remote workMid-level Full TimeHonolulu, HI, USA6h ago
-
Bash | Data Ingestion | Data Processing | Docker | GCPAsynchronous work culture | Bonus opportunity | Friendly work environment | Remote-friendlyMid-level Full TimeMilwaukee, WI, USA6h ago
-
Bash | Cloud platform | Data Processing | Docker | Google CloudAsynchronous work culture | Friendly work environment | Remote friendly distributed workMid-level Full TimeBloomington, IN, USA6h ago
-
Bash | Cloud platform | Docker | Google Cloud | Google Cloud PlatformAsynchronous culture | Flexible work environmentMid-level Full TimeDes Moines, IA, USA6h ago
-
Bash | Cloud infrastructure | Cloud platform | Data Ingestion | Data Ingestion PipelinesAsynchronous culture | Bonus | Distributed remote work | Equity | Friendly laid-back atmosphereMid-level Full TimeBuffalo, NY, USA6h ago
-
Bash | Cloud Computing | Data Processing | Docker | GCPAsynchronous culture | Flexible working style | Portfolio support | Remote-friendly environmentMid-level Full TimeNorfolk, VA, USA6h ago