Applied AI Researcher, Multi-Agent Systems

Distyl Inc.

Job Overview

Location

San Francisco

Job Type

Full-time

Full Job Description

📋 Description

• Design and build multi-agent architectures where autonomous agents coordinate through structured communication, delegation, critique, and iterative decision-making to solve complex enterprise problems.
• Investigate and formalize interaction patterns that enable agents to exchange information, refine each other’s reasoning, and collaboratively execute mission-critical workflows across distributed systems.
• Develop systems that dynamically route information and allocate tasks among agents with heterogeneous knowledge, perspectives, and reasoning capabilities.
• Research and implement communication protocols that enhance coordination efficiency, reduce redundancy, and improve decision fidelity in multi-agent collectives.
• Experiment with agent orchestration frameworks that integrate evaluator agents, feedback loops, and mixed-initiative planning to optimize collective performance over time.
• Apply advanced techniques from multi-agent reinforcement learning (MARL), graph neural networks (GNNs), and knowledge graphs to model and improve agent collaboration dynamics.
• Translate theoretical research into production-ready prototypes that demonstrate tangible improvements in real-world enterprise systems, such as supply chain logistics, patient care pathways, or customer interaction workflows.
• Work directly with enterprise customers in telecom, healthcare, insurance, manufacturing, and consumer goods to understand their mission-critical operational challenges and co-design AI-native solutions.
• Conduct experiments to validate the effectiveness of multi-agent systems against real business metrics, ensuring measurable impact on throughput, accuracy, and reliability.
• Leverage modern AI tools daily — including ChatGPT, Cursor, and Perplexity — to accelerate research iterations, automate literature review, and prototype ideas with speed and precision.
• Communicate research findings and system outcomes directly to F500 executives and AI leaders, prioritizing demonstrable results over theoretical elegance.
• Maintain a bias toward showing, not telling: deliver functional, working systems that prove the value of multi-agent coordination in live environments within weeks, not years.
• Collaborate with cross-functional teams including software engineers, product managers, and domain experts to integrate agent systems into existing enterprise infrastructure.
• Contribute to the company’s internal research pipeline by documenting novel architectures, publishing findings, and contributing to open-source or public-facing research outputs.
• Stay at the forefront of emerging literature and breakthroughs in agent-based systems, continually integrating new methodologies into Distyl’s proprietary research framework.
• Operate in an AI-native way: treat AI not as a tool but as a co-architect in the research process, using it to generate hypotheses, simulate agent interactions, and analyze results at scale.
• Contribute to building the design language of enterprise multi-agent systems — defining standards for how agents communicate, delegate, and evolve their collaborative behaviors.
• Maintain a 100% production deployment mindset: every prototype must be engineered to scale, monitor, and sustain performance under enterprise-grade load and reliability requirements.
• Participate in hybrid work model with 3+ days per week in the San Francisco office (Tuesday–Thursday) to enable deep collaboration with the research team and enterprise partners.

🎯 Requirements

• Built or studied systems where multiple agents collaborate through structured communication, delegation, critique, or iterative coordination
• Experience with agent orchestration, communication protocols, evaluator agents, or systems where multiple agents interact to exchange information, critique reasoning, and coordinate decisions over time
• Experience with research in related fields, such as multi-agent reinforcement learning (MARL), graph neural networks (GNNs), knowledge graphs, or mixed-initiative planning
• Proven track record of research results through publications, public repositories, or demonstrable projects
• Strong programming and data analysis skills to build and test prototypes of multi-agent systems
• Uses AI tools like ChatGPT, Cursor, and Perplexity daily to accelerate research and workflow

🏖️ Benefits

• Base salary range of $150K – $250K, depending on experience, location, and level, plus meaningful equity
• 100% covered medical, dental, and vision for employees and dependents
• 401(k) with commuter benefits and in-office lunch
• Access to state-of-the-art AI models and generous usage of modern AI tools
• Ownership of high-impact projects across top enterprise customers
• Mission-driven, fast-moving culture that prizes curiosity, pragmatism, and excellence

Skills & Technologies

Rails

Hybrid

$150k-250k

Ready to Apply?

Apply Externally

You will be redirected to an external site to apply.

Distyl Inc.

Visit Website

About Distyl Inc.

Distyl is a cloud-native platform designed to simplify and accelerate the development and deployment of machine learning (ML) models. It provides a unified environment for data preparation, model training, versioning, and deployment, enabling data scientists and ML engineers to move from experimentation to production faster. The platform offers features such as automated data pipelines, managed training infrastructure, and scalable model serving. Distyl aims to reduce the complexity and operational overhead associated with MLOps, allowing organizations to focus on building and deploying impactful ML solutions. It supports various ML frameworks and integrates with existing cloud infrastructure.

View Company Profile

Get more remote jobs like this

Subscribe to the weekly newsletter for similar remote roles and curated hiring updates.

Weekly remote jobs and featured talent.

No spam. Only curated remote roles and product updates. You can unsubscribe anytime.