Future of Life Organizations - Research Engineer - Novel AI Platforms for Multiscale Alignment
Upload My Resume
Drop here or click to browse · Tap to choose · PDF, DOCX, DOC, RTF, TXT
Requirements
• 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 • 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
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 • $140,000 - $210,000 a year • plus good benefits if a U.S.-based employee
No credit card. Takes 10 seconds.