SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Spectrum Labs (operating as Alice) is seeking a Senior Responsible AI Researcher to lead cutting-edge research at the intersection of frontier AI models, Trust & Safety, model evaluation, and adversarial robustness. This role combines deep academic rigor with practical AI safety challenges in a rapidly evolving landscape.
You will drive self-initiated research initiatives and design evaluation methodologies for emerging risks including persuasion, manipulation, sycophancy, and agentic safety. Key responsibilities include:
**Frontier AI Safety & Evaluation**: Design, build, and deploy evaluation frameworks, benchmarks, and "Agentic Safety Gyms" to measure model capabilities and vulnerabilities across diverse risk domains (hate speech, misinformation, election preparedness, IP/copyright, child safety). Develop advanced adversarial prompting methodologies, red-teaming strategies, and behavioral suites to stress-test LLMs, multimodal systems, and AI agents. Investigate emerging safety risks including bias, jailbreaking tactics, and behavioral vulnerabilities.
**Research Leadership & Impact**: Lead high-impact collaborative research with top academic institutions (Oxford, Harvard, MATS, GovAI) and industry partners (OpenAI, Google DeepMind, Anthropic, Microsoft, Nvidia). Represent the organization as a thought leader at international conferences and AI safety summits. Publish groundbreaking research in top-tier AI and safety venues.
**Strategic Collaboration**: Partner with Product, Engineering, GTM, Policy, and Delivery teams to translate research into scalable safety products and client-facing offerings. Engage directly with enterprise clients to translate safety requirements into actionable research questions and evaluation suites.
**Mentorship**: Provide technical leadership to junior researchers, data scientists, and engineers. Integrate social science, policy, and technical perspectives into robust safety tooling.
**Requirements**
Must Haves:
- PhD in Science, Technology and Society Studies (STS), Machine Learning, AI Ethics, Social Data Science, or closely related research domain
- Demonstrated academic excellence with strong portfolio of peer-reviewed publications and conference presentations at top-tier venues (NeurIPS, ICML, ICLR, ACL, IEEE, CVPR, or dedicated AI Safety conferences)
- Substantial experience in AI Safety, Responsible AI (RAI), Trust & Safety, or Model Evaluation
- Strong hands-on capabilities in Python and modern ML/DL frameworks (PyTorch, Transformers)
- Deep working knowledge of foundation models (LLMs, Text-to-Image, Multimodal), agents, reasoning systems, and current safety mitigation techniques
- Proven experience designing datasets, benchmark suites, red-teaming protocols, or synthetic simulation platforms
- Proven track record of self-initiating research projects and bringing in external partnerships
- Excellent verbal and written communication skills; ability to convey complex technical concepts to non-technical stakeholders and executives
- Ability to operate across technical data science, social science paradigms, and product execution
Preferred Qualifications:
- Prior employment, consulting, advisory, or formal research collaboration with frontier AI labs (OpenAI, Anthropic, Google DeepMind, Meta AI) or leading safety research collectives (MATS, GovAI)
- Experience in domain-specific safety applications such as election integrity, psychological manipulation, or agentic behavioral safety suites
