AI Engineer - Multi-Agent LLM Security Systems

CipherData, Inc.; Bellevue (WA); On-site; USD 120,000 - 160,000; Full time

Job summary

CipherData, Inc. in the Greater Seattle Area is seeking an AI Engineer to own the core multi-agent reasoning layer that turns telemetry from 70+ security vendors into actionable conclusions for analysts.

You’ll design agent architectures, run experiments to decide which ideas ship, and deploy in production where SOC teams rely on reliable, low-latency results. Collaborate with security researchers and engineers to frame problems, validate outcomes, and balance performance with cost, accuracy,

Qualifications

• Hands‑on experience designing and building LLM applications (agents, RAG, orchestration, etc.)
• Strong software engineering fundamentals in Python
• Experience building LLM workflows with various agent frameworks
• Experience evaluating and improving LLM output quality, both qualitatively and quantitatively
• Comfort defining ambiguous problems, experimenting quickly, and making data-driven decisions

Responsibilities

• Build our multi-agent LLM system by designing and improving the core system where multiple LLM agents collaborate to detect, investigate, and correlate threats.
• LLM orchestration: Build pipelines that coordinate multiple models against cost, latency, and accuracy trade-offs.
• Evaluation & continuous improvement: Create evaluation systems that measure agent output quality and feed data back as learning signals.
• Reliability: Experiment with prompting, architecture, and verification strategies to reduce hallucination and improve stability.
• Build what’s next: Expand into automated response, deeper threat correlation, and new product areas.

Skills

LLM applications

Python

LLM workflows

LLM evaluation

Data-driven decisions

Job description

CipherData, Inc. in the Greater Seattle Area is seeking an AI Engineer to own the core multi-agent reasoning layer that turns telemetry from 70+ security vendors into actionable conclusions for analysts.

You’ll design agent architectures, run experiments to decide which ideas ship, and deploy in production where SOC teams rely on reliable, low-latency results. Collaborate with security researchers and engineers to frame problems, validate outcomes, and balance performance with cost, accuracy,