Full-time | Remote | R\&D | Reports to Chief AI Safety Architect
About Elloe
Elloe is the trust layer for AI.
We sit between the world’s most powerful language models and the institutions that can't afford to get it wrong — hospitals, banks, regulators. We trace and block failures in real time. That’s not marketing — we’re deployed at the European Commission, with NIH clinical trials, and inside a Top-5 EU bank catching GDPR violations live.
This is the enforcement layer GenAI has been missing. We're not visualizing problems — we're fixing them.
About the Role
You’ll define the constitutional logic for self-governing AI. From SPAG enforcement layers to SHAP-governed inference decisions, this role is foundational to our AGI alignment infrastructure.
What You’ll Own
1. Constitutional AI Systems
- Architect SPAG: Self-Patching AGI Governor for aligned reasoning agents
- Formalize logic for regional overrides, zero-trust inference, and SHAP audits
2. Multi-Agent Regulatory Alignment
- Coordinate Security, Engineering, and Compliance teams on policy behavior
- Define protocol-level constraints and override conditions for constitutional agents
3. Governance Trials & Papers
- Publish with our Council on AI Safety & Infrastructure
- Collaborate with EU, NIST, and FTC on AGI audit protocols
Who You Are
- PhD in AI Safety, Formal Methods, or Governance
- Experience in alignment, RLHF, or constitutional AI design
- Deep understanding of SHAP, auditability, or red-teaming systems
Why This Matters
Our competitive edge isn’t just AI — it’s defensible enforcement. This role turns that into product.
You’ll Leave This Role With
- Referenceable contributions to enforcement infra that’s live in EU and US institutions
- First-hand product work across legal, engineering, and GTM teams
- Influence over how regulatory primitives become systems people trust
Logistics & Application
- Start Date: Flexible (Q3–Q4 ideal)
- Location: Remote-first; timezone overlap with NY or EU preferred
- Compensation: Top of market salary + equity
- To Apply: Send a short note on the governance primitives you'd be most excited to formalize.
