Skip to main content

Research Engineer, AI Safety & Alignment

Summary by AIEngineer.careers

Research Engineer, AI Safety & Alignment is a AI Safety Engineer role (full-time). with Character.AI. in REDWOOD CITY, US. Compensation shown: $225K–$400K. Imported listing (source: feeny.ai). Apply on the employer's site (feeny.ai).

Imported listing (source: feeny.ai) · Apply on feeny.ai

How our listings work

REDWOOD CITY · US
$225K–$400K
Full-time
SENIOR
Apply Now

More AI jobs in United States

The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.

Imported job description

Sourced from feeny.ai

Character.AI is hiring a Research Engineer for its Safety team to tackle AI safety and alignment for large language models. You will bridge theoretical research and practical application, writing production-quality code to test hypotheses and integrating safety solutions into products. The role focuses on evaluation methodologies, alignment techniques, interpretability, and adversarial testing to make models more robust, honest, and harmless.

Responsibilities

  • Develop and implement novel evaluation methodologies and metrics to assess safety and alignment of large language models
  • Research and develop techniques for model alignment, value learning, and interpretability
  • Conduct adversarial testing to uncover vulnerabilities and failure modes
  • Analyze and mitigate biases, toxicity, and harmful behaviors using RLHF and fine-tuning
  • Collaborate with engineering and product teams to translate safety research into scalable solutions
  • Stay current with AI safety research and contribute to the academic community through publications

Requirements

  • PhD or equivalent experience in Computer Science, Machine Learning, or a related field
  • Ability to write clear, clean production-facing and training code
  • Experience working with GPUs for training, serving, and debugging
  • Experience with data pipelines and data infrastructure
  • Strong understanding of transformers and reinforcement learning with a focus on safety implications
  • Passion for responsible AI development and solving complex safety challenges

Nice to Have

  • Experience with product experimentation and A/B testing
  • Experience training large models in a distributed setting
  • Familiarity with ML deployment and orchestration (Kubernetes, Docker, cloud)
  • Experience with explainable AI and interpretability techniques
  • Research in AI safety, alignment, ethics, or a related area
  • Knowledge of societal and ethical implications of AI, including policy and governance
  • Publications in relevant ML journals or conferences

Tech Stack

A/B TestingDockerFine-tuningGPUInterpretabilityKubernetesPyTorchReinforcement LearningRLHFTransformers
Character.AI

Character.AI

Redwood City · US · 314+ employees

Character.AI is a leading artificial intelligence company that provides an open-ended conversational platform. It allows users to create, interact with, and share AI-driven characters for entertainment, storytelling, and creative expression.

Weekly job alert

Get a weekly email when new AI engineering jobs match your filters. Free — confirm your address to start.

Related Jobs