SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Spectrum Labs (trading as Alice) is seeking a Senior AI Researcher to lead post-training evaluation, red-teaming, and reinforcement learning (RL) gym audits on open-weight models. You will establish rigorous benchmarking methodologies, evaluate large language models (LLMs) against complex security threats like Indirect Prompt Injections (IPI), and construct post-training evaluation pipelines that accurately measure frontier-level security capabilities.
Key Responsibilities:
• RL Post-Training & Benchmarking: Execute post-training runs (e.g., GRPO) using mainstream open-weight generalist models against security-focused RL environments, targeting threat vectors like Indirect Prompt Injection (IPI).
• Reward Diagnostics & Trace Analysis: Analyze live loss curves and rollout traces to identify reward hacking, lazy policy convergence, and flawed or over/under-specified verifiers.
• Task & Environment Auditing: Review tasks and multi-turn environments (including tool use, web navigation, and computer use) for realism, threat model accuracy, data distribution, and dataset balance.
• Performance Reporting: Generate comprehensive evaluation cards detailing hill-climbing performance uplift across checkpoints, failure modes, tokens/turns per rollout, and task-level success rates.
• Integration & Orchestration: Integrate dockerized environments (e.g., Harbor format) into internal training frameworks, optimizing reset/statefulness semantics, concurrency, and throughput ceilings.
About the Company:
Alice is a trust, safety, and security company built for the AI era. The company safeguards communicative technologies across the entire AI lifecycle, supporting frontier model labs, enterprises, and user-generated content platforms with model hardening evaluations, pre-deployment red-teaming, runtime guardrails, and drift detection. Alice is recognized as a global leader in online safety and AI security.
Requirements:
Required Qualifications:
• M.S. or Ph.D. in Data Science, Machine Learning, Computer Science, or equivalent practical experience in deep learning
• Strong hands-on experience training large-scale models using RL algorithms (e.g., GRPO, PPO) on open-weight architectures
• Solid understanding of LLM vulnerabilities, red-teaming methodologies, and defensive alignment against IPI attacks
• Proficiency in PyTorch, Docker containerization, and distributed training architectures
• Ability to analyze agent rollout traces, craft deterministic rubrics/verifiers, and debug complex reward shaping flaws
Preferred Qualifications:
• Prior experience working with standard RL gym formats, such as Harbor
• Experience evaluating complex agentic workflows in tool-use or web-browser environments
• Familiarity with evaluating open-weight models similar to Llama or Mistral against adversarial workloads
