Top Tech Jobs & Startup Jobs

Lead a multidisciplinary red teaming team to design and run adversarial tests, evaluate model risks, produce high-quality deliverables, and communicate findings to clients while improving methodologies and workflows.

Create adversarial prompt-injection tasks in YAML for RL Gym environments: define agent personas, simulated environments, adversarial payloads, benign user requests, run tasks against frontier models, validate success rates, and submit passing tasks with deterministic evaluation criteria.

Lead product strategy to convert Trust & Safety workflows into scalable, agentic, enterprise-ready offerings. Drive 0-to-1 incubation, productization, and scaling for large platforms, maintain defensible data assets, and collaborate with Professional Services to deliver bespoke projects while ensuring high-throughput adoption by Big Tech clients.

Analyze content infringements and write adversarial prompts to find model vulnerabilities across LLMs, text-to-image/video, and agents. Manage datasets and projects end-to-end, investigate evasion tactics, collaborate with engineering, product, and policy teams, and promote knowledge sharing to improve model safety.

The Account Manager will oversee 8-figure enterprise accounts, manage strategic relationships, identify growth opportunities, and communicate technical results to non-technical executives.

Conduct OSINT and deep-web data mining to identify mobile threats; analyze large datasets with scripting, statistics, and AI techniques; monitor forums and dark web; translate findings into intelligence reports and actionable detection/enforcement recommendations; collaborate with technical teams to automate data collection and build lightweight tools.

The role involves conducting simulated cyber attacks, vulnerability assessments, risk analyses, and developing mitigation strategies for AI security technologies.

Lead a team of malware researchers, manage security research projects, enhance team reports, and collaborate on threat detection and response.

Join Alice.io as a GenAI Expert to design adversarial prompts and create diverse prompts that challenge AI systems, ensuring safety insights and cultural nuances. Native language fluency is preferred.

Conduct OSINT/WEBINT investigations to detect and mitigate online threats, analyze cyber patterns, prepare reports, and collaborate with the research team.