Remote AI Explainability & Alignment Engineer (SHAP)

Elloe AI; Austin (TX); Hybrid; USD 180,000 - 260,000; Full time

Benefits offered by this job

Salary + equity

Job summary

Elloe AI is seeking a Member of Technical Staff – AI Research Engineer to own SHAP-driven explainability and alignment systems for GenAI in regulated industries. You will design SHAP-based explanations, run alignment experiments, and deploy explainability dashboards for internal and customer use.

Role requires strong research-to-production instincts, familiarity with SHAP/LIME, and the ability to ship aligned features end-to-end in a remote, full-time setting.

Qualifications

• Strong research-to-production instincts with MS/PhD in a relevant field.
• Experience designing SHAP-based explanations and model alignment.
• Ability to ship explainability features and dashboards end-to-end.

Responsibilities

• Design SHAP-based explanation layers for GenAI outputs.
• Architect AutoHeal interventions for misaligned models.
• Build alignment experiments grounded in real-world data.
• Own deployment of explainability dashboards for internal and customer use.

Skills

SHAP

LIME

Explainability libraries

Alignment experiments

End-to-end deployment

Education

PhD in CS/EECS or related

Tools

SHAP

LIME

Job description

Elloe AI is seeking a Member of Technical Staff – AI Research Engineer to own SHAP-driven explainability and alignment systems for GenAI in regulated industries. You will design SHAP-based explanations, run alignment experiments, and deploy explainability dashboards for internal and customer use.

Role requires strong research-to-production instincts, familiarity with SHAP/LIME, and the ability to ship aligned features end-to-end in a remote, full-time setting.