Research Engineer - Novel AI Platforms for Multiscale Alignment (AI)

TL;DR

Research Engineer - Novel AI Platforms for Multiscale Alignment (AI): Develop novel AI platforms addressing alignment challenges and practical LLM agents with an accent on agent-based systems and multi-objective optimization. Focus on designing multi-agent dynamics, cooperative AI architectures, and technical infrastructure for safety research.

Location: Anywhere (Open Globally), Remote. US work authorization required for employees; international candidates as independent contractors. No visa sponsorship.

Salary: $140,000 - $210,000 a year plus good benefits if a U.S.-based employee

Company

The Center for AI Risk Management & Alignment (CARMA) works to lower risks from transformative AI through rigorous analysis, policy frameworks, technical safety approaches, and global perspectives on durable safety.

What you will do

• Research and develop AI systems and platforms for safety research, internal tooling, and safety community support
• Design and implement architectures for agent execution environments and interaction platforms
• Develop optimization algorithms for multi-objective and cooperative AI systems
• Create mechanisms for conflict resolution and preference aggregation in multi-agent settings
• Build middleware for secure agent communication and reusable components for AI alignment research
• Collaborate on technical publications, document architectures, and support evaluation of research prototypes

Requirements

• MS or PhD in Computer Science, AI, or related field (or equivalent experience)
• Experience with dynamic plan recognition, activity recognition, dynamic multicriteria decision making, multi-agent systems, or AI builder platforms
• Strong programming skills in Python and Java
• Demonstrated ability to independently drive technical projects from concept to implementation
• Familiarity with AI alignment, control, safety techniques
• Experience developing middleware, frameworks, or platforms; breadth in ML and AI systems architecture
• Literate in semi-formal semantics; excellent communication and technical documentation skills

Nice to have

• Publications in AI alignment or safety
• Experience with LLMs in agent architectures, distributed systems, security/privacy in multi-party computation
• Knowledge of game theory, social choice theory, metacognitive systems
• Open source contributions; building systems managing trade-offs between objectives

Culture & Benefits

• Equal opportunity employer focused on merit-based hiring
• Inclusive organization promoting equal opportunities
• Good benefits for U.S.-based employees