LogoFresh Jobs Ahead
ActiveFence
ActiveFence
201 – 500 Employees
Artificial IntelligenceCybersecurity
ActiveFence is a cybersecurity and artificial intelligence company focused on trust and safety for online platforms. Its full-stack offering combines intelligence research, AI-powered detection of harmful content, and content moderation tools to help platforms address risks such as child exploitation, disinformation, hate speech, terrorism, nudity, fraud, and other forms of online harm. ActiveFence supports trust and safety teams of different sizes, helping protect more than three billion users worldwide across over 100 languages.
LinkedIn
Company Jobs

Senior AI Researcher – Hybrid in Israel

Lead reinforcement learning evaluation, red-teaming, and security audits for open-weight AI models. Build benchmarking and post-training pipelines for ActiveFence’s AI trust, safety, and security work.

ILIsraelHybridFull-timeSeniorEnglish RequiredAI Research ScientistMachine Learning Engineer
DockerPyTorch

Description

  • Lead post-training evaluations, red-team exercises, and reinforcement learning gym audits for open-weight models
  • Design rigorous benchmarking methodologies
  • Assess large language models against sophisticated threats, including Indirect Prompt Injection attacks
  • Build post-training evaluation pipelines that measure realistic frontier-level security capabilities
  • Run post-training experiments such as GRPO with open-weight generalist models in security-focused reinforcement learning environments
  • Examine live loss curves and rollout traces to detect reward hacking, lazy policy convergence, and poorly specified verifiers
  • Assess tasks and multi-turn environments involving tool use, web navigation, and computer use for realism, threat-model accuracy, data distribution, and dataset balance
  • Produce evaluation cards covering checkpoint performance gains, failure modes, rollout tokens and turns, and task-level success rates
  • Integrate Dockerized environments, including Harbor-format environments, into internal training frameworks
  • Improve reset and statefulness semantics, concurrency, and throughput limits

Requirements

  • M.S. or Ph.D. in Data Science, Machine Learning, Computer Science, or equivalent practical deep learning experience
  • Hands-on experience training large-scale models with reinforcement learning algorithms such as GRPO or PPO on open-weight architectures
  • Strong knowledge of LLM vulnerabilities, red-teaming practices, and defensive alignment against Indirect Prompt Injection attacks
  • Proficiency with PyTorch, Docker containerization, and distributed training architectures
  • Ability to interpret agent rollout traces, create deterministic rubrics and verifiers, and debug complex reward-shaping issues
  • Experience with standard reinforcement learning gym formats such as Harbor is preferred
  • Experience assessing complex agentic workflows in tool-use or web-browser environments is preferred
  • Familiarity with evaluating Llama-like or Mistral-like open-weight models against adversarial workloads is preferred

Related Jobs