Description
SpaceXAI is seeking a skilled AI Humanities Specialist to enhance its models by providing high-quality data annotations and inputs tailored to humanities contexts.
In this role, you will leverage your expertise in fields such as linguistics, history, classical studies, literature, poetry, philosophy, ethics, visual arts, and performing arts to support the training of Grok. You will evaluate model outputs and create training data so Grok reasons accurately, weighs evidence carefully, and communicates uncertainty honestly. This work is grounded in scholarly judgment, not creative writing.
Responsibilities:
- Evaluate model outputs in your field for factual accuracy, logical coherence, fallacious reasoning, and hidden assumptions.
- Flag confident-sounding errors, anachronism, misused sources, ideological slant, and claims that outrun the evidence.
- Create exemplary responses and datasets that show intellectual honesty, careful source evaluation, and a clear distinction between primary evidence, secondary interpretation, and speculation.
- Steel-man opposing views before criticizing them, and mark what is settled, contested, or unknown.
- Ground annotations and reference answers in primary sources whenever they exist, then weigh secondary scholarship against that record.
- Collaborate with engineering teams to design evaluation tasks, rubrics, and examples that test and strengthen Grok’s behaviour and personality in the humanities.
- Help define what good model behaviour looks like in contested humanistic questions: precise, sourced, proportionately confident, and resistant to fashionable or motivated readings.
Basic Qualifications:
- Deep knowledge in at least one of the following: linguistics, history, classical studies, literature, poetry, philosophy, ethics, visual arts, or performing arts.
- Ability to assess arguments for validity, soundness, hidden premises, and category errors, not only for surface correctness.
- Habitual reliance on primary sources, with skill at weighing them against secondary literature.
- Ability to steel-man opposing views and separate settled knowledge from interpretation or speculation.
- Excellent analytical writing in English: clear, precise, and calibrated to the strength of the evidence.
- Comfort working from evolving instructions to produce annotations, critiques, and reference answers at a consistently high standard.
Preferred Skills and Experience:
- PhD in one of the listed fields, or equivalent demonstrated scholarly depth.
- Published analytical work, such as peer-reviewed articles, monographs, critical editions, catalog essays, or other rigorously sourced scholarship.
- Experience in teaching, academic peer review, archival research, textual criticism, historiography, or formal argument analysis.
- Range across more than one listed field, or across historically and culturally distinct canons within a field.
- Familiarity with evaluating AI or LLM outputs, building benchmarks, or creating training data.
- Public writing or lectures that make difficult humanistic material accurate without flattening it.
Location and Other Expectations:
- Tutor roles may be offered as full-time, part-time, or contractor positions, depending on role needs and candidate fit.
- For contractor positions, hours will vary widely based on project scope and contractor availability, with no fixed commitments required.
- Tutor roles may be performed remotely from any location worldwide, subject to legal eligibility, time-zone compatibility, and role-specific needs.
Compensation and Benefits:
- US-based candidates: $35/hour - $75/hour depending on factors including relevant experience, skills, education, geographic location, and qualifications.
- Benefits vary based on employment type, location, and jurisdiction. Benefits for eligible U.S.-based positions include health insurance, 401(k) plan, and paid sick leave.
This listing is enriched and indexed by YubHub. To apply, use the employer's original posting:
https://job-boards.greenhouse.io/xai/jobs/5227951007