Principal AI Engineer

Swimlane is looking for a Principal AI Systems Engineer to lead the evolution of its AI SOC capabilities. This is a highly technical, hands-on engineering role focused on building production-grade multi-agent systems, AI-powered security copilots, and intelligent automation workflows.
Unlike traditional AI roles centred around model training, this position focuses on architecting, integrating, evaluating, and operating enterprise-scale LLM systems that solve real-world security operations challenges.
The candidate will have responsibilities across the following functions:
Agentic AI Architecture:
Design and build production-grade multi-agent systems for Security Operations (SOC).
Develop AI-powered security copilots, autonomous workflows, and intelligent chat interfaces.
Drive the transition from prompt-based applications to robust agent-based architectures.
Applied LLM Engineering
Build enterprise-grade AI workflows for: Alert triage, Incident investigation, Security summarisation, Workflow automation, Threat intelligence enrichment.
Implement advanced context engineering and tool-using agent patterns.
Integrate external tools, APIs, and enterprise systems using MCP and secure tool-calling frameworks.
AI Evaluation and Reliability:
Build evaluation harnesses and testing frameworks.
Define and measure: Accuracy, Faithfulness, Latency, Cost, Reliability, Safety
Conduct regression testing across AI workflows and agent systems.
AI Security and Governance:
Implement AI guardrails and secure agent architectures.
Design defences against: Prompt injection, Tool abuse, Data leakage, Unauthorised access.
Ensure auditability, privacy, and governance across AI workflows.
Technical Leadership:
Drive architecture decisions and engineering best practices.
Mentor engineers and establish standards for: Context engineering, RAG architecture, Tool integrations, Agent evaluation, Production AI systems
Requirements:
8+ years of software engineering experience building production systems.
Strong system design and architecture experience.
Proven track record leading complex engineering initiatives.
Strong hands-on coding expertise in: NET (C#), Python, and TypeScript.
Hands-on experience building: Multi-agent systems, AI copilots, Enterprise chatbots, Tool-using agents, AI-powered automation platforms
Strong experience with: AWS Bedrock (highly preferred), Claude Agent SDK, OpenAI SDK, Enterprise LLM deployments
Deep expertise in: RAG architectures, Vector databases, Semantic retrieval, Context engineering, MCP integrations, Tool orchestration
Experience building: Evaluation harnesses, Benchmarking frameworks, Quality measurement pipelines, Automated testing for AI workflows.
Strong understanding of: AI security frameworks, Prompt injection prevention, Secure tool calling, Agent governance, Data privacy, Auditability.
Good to Have:
Cybersecurity domain experience.
SOC / SIEM / SOAR products.
Threat Intelligence platforms.
Detection Engineering.
Incident Response workflows.
AI Governance platforms.
Agent sandboxing.
Policy-based tool control.
AI coding tools such as Cursor, Claude Code, and GitHub Copilot.
Ideal Candidate Background:
Experience building AI systems for cybersecurity use cases.
Contributions to open-source AI projects.
Experience evaluating and benchmarking LLMs and agent frameworks.
Familiarity with LangGraph, CrewAI, AutoGen, Semantic Kernel, or similar agent orchestration frameworks.

Experience
7-11 yrs