About this role
Distyl AI seeks an Applied AI Researcher on its Multi-Agent Systems team to advance how collaborating agents coordinate, reason and execute complex enterprise workflows. The team researches architectures that enable agents with different views of a problem to work together across multiple reasoning processes.
Responsibilities
- Design systems that structure agent communication, route information and coordinate decision-making.
- Investigate how agents exchange information, critique and refine one another’s reasoning, delegate work and coordinate execution over time.
- Identify effective interaction patterns and build prototypes and experiments that demonstrate their value on practical enterprise problems.
Requirements
- Experience building or studying systems in which multiple agents collaborate through structured communication, delegation, critique or iterative coordination, including experience with agent orchestration, communication protocols, evaluator agents or similar interacting-agent systems.
- Research experience in related areas such as multi-agent reinforcement learning, graph neural networks, knowledge graphs or mixed-initiative planning.
- A demonstrated record of research results, whether through publications or other publicly shared work; strong programming and data analysis skills to prototype ideas and evaluate them experimentally.
- Daily use of AI tools such as ChatGPT, Cursor and Perplexity, and an interest in practical demonstrations of advances in agent coordination rather than benchmark improvements alone. The posting specifies no degree or minimum number of years of experience.
Location and compensation:
- The role is listed in San Francisco and New York and follows a hybrid model with 3+ in-office days per week, including Tuesday–Thursday.
- Base salary is $150K–$250K, depending on experience, location and level. The role is eligible for equity and benefits including medical, dental and vision coverage for employees and dependents, flexible time off, retirement and financial-planning benefits, wellness and family-building benefits, and in-office lunches and snacks.
Skills for this role
Multi-agent systemsAgent orchestrationCommunication protocolsEvaluator agentsMulti-agent reinforcement learningGraph neural networksKnowledge graphsMixed-initiative planningProgrammingData analysisResearchPrototypingExperimental designChatGPTCursorPerplexity