Applied AI Research Engineer: Agentic Systems

Distyl; San Francisco (CA); Hybrid; USD 150,000 - 250,000; Full time

Benefits offered by this job

Equity

Medical, dental & vision insurance

Flexible time off

Retirement planning & 401(k)

Wellness benefits

Free in-office lunches

Job summary

Distyl AI is hiring Research Engineers to bridge frontier AI research and production systems. You will design and implement agentic AI systems, prototype robust architectures, and work with researchers and engineers to deploy reliable solutions in real customer environments.

You will build evaluation frameworks, observe system behavior, and ensure deployment safety across enterprise workflows in a hybrid setup with in-office collaboration several days a week.

Qualifications

• Experience building AI systems using models, tools, retrieval, planning, memory, or multi-step execution.

Responsibilities

• Design, prototype, and implement agentic AI systems across complex enterprise workflows.
• Build compound AI architectures combining planning, tool use, retrieval, memory, evaluation, orchestration, and execution.
• Investigate how agents reason, coordinate, recover from errors, and interact with external systems.
• Develop evaluation frameworks measuring agent behavior, task completion, reliability, and failure modes.
• Create tools to observe, debug, test, and improve agent behavior.
• Collaborate with AI Researchers and AI Engineers to productionize approaches.

Skills

Agentic AI systems

Strong Python

Systems-level reasoning

Research mindset

AI-native working style

Show-and-tell demonstrations

Customer-facing experience

Ownership mentality

Tools

Python

Job description

Distyl AI is hiring Research Engineers to bridge frontier AI research and production systems. You will design and implement agentic AI systems, prototype robust architectures, and work with researchers and engineers to deploy reliable solutions in real customer environments.

You will build evaluation frameworks, observe system behavior, and ensure deployment safety across enterprise workflows in a hybrid setup with in-office collaboration several days a week.