Job Description
Are you ready to architect the ethical foundations of tomorrow? Nexus Future Tech is seeking a visionary Senior AI Safety Engineer to join our elite research division. As we push the boundaries of Artificial General Intelligence (AGI) in preparation for the 2026 era, you will be the gatekeeper of alignment, ensuring our systems are not only powerful but safe, interpretable, and beneficial for humanity.
In this pivotal role, you will bridge the gap between cutting-edge machine learning research and rigorous safety engineering. You will develop robust frameworks to mitigate risks associated with autonomous agents, ensuring our AI operates within defined ethical boundaries while delivering unprecedented value.
Why Join Us?
- Work on the frontier of AI safety with a team of world-class researchers.
- Competitive compensation and equity packages for top-tier talent.
- Flexible remote-first culture with a hub in San Francisco.
- Direct impact on the trajectory of AGI development.
Responsibilities
- Design Safety Frameworks: Develop and implement novel adversarial testing protocols and red-teaming strategies for Large Language Models (LLMs) and autonomous agents.
- Risk Assessment: Conduct deep-dive analysis on model outputs to identify and mitigate potential biases, hallucinations, and malicious use cases.
- Alignment Research: Collaborate with ML researchers to define and enforce safety constraints during the training and fine-tuning phases.
- Tool Development: Build open-source tools and libraries that the broader AI community can use to audit and improve model safety.
- Policy Definition: Draft internal guidelines and safety documentation regarding the deployment of AI systems in high-stakes environments.
- Stakeholder Communication: Translate complex technical safety findings into clear, actionable insights for non-technical leadership and product teams.
Qualifications
- Education: PhD, Master’s degree, or equivalent experience in Computer Science, Mathematics, Philosophy, or a related technical field.
- Experience: Minimum of 5 years of professional experience in machine learning, AI research, or cybersecurity.
- Technical Skills: Proficiency in Python, PyTorch, or TensorFlow. Experience with LLMs (e.g., GPT-4, Claude, Llama) is highly preferred.
- Ethical Reasoning: Strong understanding of AI ethics, machine learning theory, and the specific challenges of alignment.
- Problem Solving: Demonstrated ability to tackle novel, undefined problems with creative and rigorous solutions.
- Communication: Excellent written and verbal communication skills, with the ability to articulate complex technical concepts to diverse audiences.