Member of Technical Staff - Explainability Engineer

Role Description

You’ll own the design of SHAP-driven explainability and model alignment systems for GenAI in high-stakes industries. From human-in-the-loop correction to production-grade dashboards, you’ll architect and ship the critical loops that make AI traceable, safe, and compliant for real-world GenAI. This means:

• SHAP-layer visualizations
• Alignment experiments with AutoHeal
• Deeply integrating human feedback into every model correction
• Owning core loops that power how Elloe learns to heal itself

Qualifications

• MIT/Harvard (CS, EECS, HST) with strong research-to-production instincts
• Familiar with SHAP, LIME, or other explainability libraries
• Able to design alignment experiments that are both empirical and operational
• Thrive in ambiguity and ship aligned features end-to-end

Requirements

• Design and implement SHAP-based explanation layers for GenAI outputs
• Architect AutoHeal interventions for misaligned model behavior
• Build alignment experiments grounded in real-world compliance datasets
• Own deployment of explainability dashboards for internal and customer usage

Benefits

• Founder-level ownership on compliance AI infra
• A deep technical legacy in one of GenAI’s most urgent domains
• Equity in a company built to define real-world alignment
• A public portfolio of traceable, explainable AI systems

Logistics & Application

• Compensation: Salary + equity
• Commitment: Full-time or intense part-time (15+ hrs/week)
• Start: Rolling (ideal: within 2–4 weeks)
• To Apply: Tell us how you'd extend SHAP to make multi-modal outputs traceable