Research Engineer - Novel AI Platforms for Multiscale Alignment

Job Summary

The Alignment of Dynamical Cognitive Systems program seeks a Research Engineer to develop novel AI platforms addressing critical alignment challenges and practical LLM agents. Combining platform development with alignment research, this role requires expertise in agent-based systems and multi-objective optimization. You'll co-design and develop systems supporting safety research, internal tools, and community resources -- creating environments to shape multi-agent dynamics and implement cooperative AI architectures with robust alignment properties. You'll also build technical infrastructure to investigate experimental AI alignment and control approaches while collaborating with researchers to bring theoretical approaches into practice. This position offers the chance to develop foundational technologies essential for promoting safety as AI capabilities rapidly advance.

About CARMA

The Center for AI Risk Management & Alignment (CARMA) works to help society navigate the complex and potentially catastrophic risks arising from increasingly powerful AI systems. Our mission is specifically to lower the risks to humanity and the biosphere from transformative AI.

We focus on grounding AI risk management in rigorous analysis, developing policy frameworks that squarely address AGI, advancing technical safety approaches, and fostering global perspectives on durable safety. Through these complementary approaches, CARMA aims to provide critical support to society for managing the outsized risks from advanced AI before they materialize.

CARMA is a fiscally-sponsored project of Social & Environmental Entrepreneurs, Inc., a 501(c)(3) nonprofit public benefit corporation.

Responsibilities

Research and develop AI systems and platforms variously 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

Implement testing frameworks and example environments to validate theoretical approaches

Build middleware components that facilitate secure and efficient agent communication

Architect and develop reusable software components for AI alignment research

Document system architectures, APIs, and implementation details

Collaborate on technical publications and research presentations

Contribute to both practical implementations and theoretical research in AI alignment

Support the evaluation and refinement of research prototypes

Required Qualifications

MS or PhD in Computer Science, AI, or related field (or equivalent experience)

Experience with one or preferrably more of: dynamic plan recognition, activity recognition, dynamic multicriteria decision making, multi-agent systems, or AI builder platforms

Strong programming skills in both Python and Java

Demonstrated ability to relatively independently drive technical projects from concept to implementation

Familiarity with techniques for AI alignment, control, safety, or related research areas

Experience developing middleware, frameworks, or platforms

Breadth of experience in machine learning and AI systems architecture

Literate in semi-formal semantics

Excellent communication skills and technical documentation abilities

Preferred Qualifications

Publications (formal or informal) in AI alignment, AI safety, or related research areas

Familiarity with varied multi-objective optimization techniques

Experience with contextual pragmatics and/or constraint satisfaction problems

Developed novel multi-agent architectures

Experience with LLMs and integrating them into agent architectures

Experience with distributed systems and platform development

Knowledge of security and privacy methods for multi-party computation

Understanding of basic game theory and/or social choice theory concepts

Familiarity with metacognitive systems, metareasoning, or dynamical cognitive approaches

Demonstrable open source project contributions

Experience building systems that actively manage trade-offs between competing objectives

CARMA/SEE is proud to be an Equal Opportunity Employer. We will not discriminate on the basis of race, ethnicity, sex, age, religion, gender reassignment, partnership status, maternity, or sexual orientation. We are, by policy and action, an inclusive organization and actively promote equal opportunities for all humans with the right mix of talent, knowledge, skills, attitude, and potential, so hiring is only based on individual merit for the job. Our organization operates through a fiscal sponsor whose infrastructure only supports persons authorized to work in the U.S. as employees. Candidates outside the U.S. would be engaged as independent contractors with project-focused responsibilities. Note that we are unable to sponsor visas at this time.