AI Safety Scientist, Deep Learning
Core
Develop datasets, moderator models, and safety tools to assess and improve the safety, fairness, and security of multi-lingual Large Language Models (LLMs) and multi-modal systems.
Role type
Senior IC Deep Learning Scientist (AI Safety)
Builds
Production LLMs, datasets, and safety evaluation systems for content safety, ML fairness, and security.
Domain
Artificial Intelligence / Large Language Models / Content Safety
Deliverable
production ML models
Required skills
Deep Learning, Machine Learning algorithms, Python programming, PyTorch/Keras frameworks, Content Safety, ML Fairness, AI Model Security, Multi-lingual model development, Bias detection and mitigation, SFT/RL training techniques
Preferred skills
LLM alignment and fine-tuning, Vision Language Models (VLMs), Multimodal Content Safety, Legal and regulatory compliance, Hallucination detection, GenAI Security (Prompt Stability, Model Extraction, Adversarial Robustness), Scientific research and publication
Technologies
Python, PyTorch, Keras, LLMs, VLMs
Responsibilities
Develop datasets and moderator models for evaluating LLMs; Research and implement bias detection and mitigation techniques; Define and track key metrics for responsible LLM behavior; Contribute to repositories to develop safety tools; Collaborate with engineers and researchers on safety challenges.
Seniority
Senior, hands-on IC
