Staff AI Engineer

RadiantSecurity

About The Position

Radiant Security is building the most advanced AI SOC platform, featuring unbounded alert triage, investigation, and response for security teams at scale. Our platform ingests alerts from across an organization's entire security stack (SIEM, EDR, identity, cloud) and uses AI to triage, investigate, and surface what actually matters. We're replacing alert fatigue with clear signal, so analysts can focus on real threats. We're a small, fast-moving team. We ship continuously, stay close to customers, and hold ourselves to a high standard. Our product touches the daily workflows of security teams, and decisions we make have a direct impact on how quickly threats get resolved. Join us and boost your career with hands-on AI experience. The Role The frontier of applied AI isn't in research labs — it's in production systems solving hard problems under real constraints. As a Staff AI Engineer, you'll be at that frontier, shaping how an entire AI engineering team builds, evaluates, and scales agentic technology in one of the most technically demanding domains there is: cybersecurity. This role is for engineers who think in systems. You'll own the architecture that underpins every pipeline the team ships — defining how agents are designed, how data flows through complex DAGs, how models are evaluated and swapped, and how the whole system holds together under production load. But you'll also be the person other engineers turn to when a problem is novel, a design decision is hard, or a new capability needs to be pioneered. The best technology decisions in this space haven't been made yet. You'll make them.

Requirements

Strong programming skills; 8+ years of experience building and deploying production services end-to-end.
Extensive experience designing and shipping production AI/ML systems at scale.
Deep expertise in LLM-based agent architectures, including multi-agent orchestration and complex pipeline design.
Demonstrated ability to lead technical projects involving multiple engineers and cross-functional stakeholders.
Strong command of evaluation methodologies: statistical testing, benchmarking, regression detection, and metric design.
Excellent written and verbal communication — able to present complex technical decisions to both engineering and non-engineering audiences.
Track record of raising the engineering bar on a team through mentorship, standards, and tooling.

Nice To Haves

Domain experience in cybersecurity, threat detection, or security operations.
Experience with large-scale data pipelines and MLOps/LLMOps infrastructure.
Background in founding or significantly growing an AI engineering function.
Published work, open-source contributions, or conference presentations in the AI/ML space.

Responsibilities

Own the end-to-end architecture of agentic pipelines: how agents are structured, how data flows between them, how pipelines are composed and versioned, and how the system scales under operational demand.
Define the structural patterns for DAG-based agent orchestration.
Drive decisions on LLM selection, tool use, retrieval-augmented generation, and memory/state management at the system level.
Lead multi-engineer projects from technical scoping through delivery, coordinating across engineering, product, and security domain experts.
Set best practices for prompt versioning, agent evaluation, dataset curation, and production monitoring.
Identify and resolve systemic quality or reliability issues across the pipeline portfolio before they become production incidents.
Mentor AI Engineers on prompt optimization strategies, experimental rigor, and pipeline design patterns.
Conduct design reviews and provide actionable, constructive technical feedback.
Identify skill gaps across the team and contribute to hiring, onboarding, and growth planning.
Foster a culture of empirical decision-making — every significant change is hypothesis-driven, measured, and documented.
Stay ahead of the LLM and agentic AI landscape; assess emerging models, frameworks, and techniques for applicability to the team's roadmap.
Partner with cybersecurity leadership to translate domain needs into technical requirements and influence the product roadmap.