AI Engineering Team Lead

Armis Centrix RMS is a new product being built from scratch inside Armis (by ServiceNow). We're hiring the engineering leader who will own its AI core.

Small senior team, greenfield architecture and real production environments from day one. You'll be one of the founding technical leaders - writing code, shaping the architecture, and growing the team as the product scales.

Design and build the AI systems at the center of the product: researcher agents, deterministic runners, multi-agent orchestration across thousands of targets and hundreds of sites.

Own the full agent stack - LLM selection and behavior, RAG pipelines, tool use, memory, evaluation, and observability. Make architectural decisions that will define how the product works for years.

Drive adoption of the modern agent ecosystem: LangGraph, MCP, semantic tool discovery, hybrid edge/cloud workflows, A2A patterns. Keep pushing the frontier.

Design for progressive autonomy: pre-checks, fault tolerance, rollback, and full audit trails. In our customers' environments - critical infrastructure, enterprise security - a wrong action has real consequences.

Build the evaluation and observability pipelines that make autonomous agent behavior trustworthy and debuggable in production.

Partner with Security and DevOps on agent execution boundaries, especially across on-prem ↔ cloud data flows.

Spend most of your time in the codebase. Set the technical bar by example - architecture, code quality, and engineering judgment.

Establish standards for testing, evaluation, and safe deployment of AI systems. Build the practices that scale with the team.

Work directly with the PM and enterprise design partners to shape the roadmap. Your decisions will drive the product, not just execute it.

Start with a small senior group, grow it deliberately. Hire well, mentor, and shape the engineering culture of a startup inside a public company.

• 8+ years engineering experience with production systems, including time leading or tech-leading a team.
• Experience building a team from the ground up - first hires, culture, hiring bar.
• Shipped AI/LLM products to production - not just demos or POCs.
• Strong Python and/or TypeScript.
• Deep hands-on experience with LLMs, agent frameworks (LangGraph, Mastra, AWS Strands, Vercel AI SDK, or similar), prompt engineering, RAG, and model behavior in production.
• Distributed systems fundamentals: workflow orchestration, fault-tolerant architectures, async patterns.
• Cloud and self-hosted model deployment (Bedrock, Vertex AI, Azure OpenAI, Anthropic, Ollama).
• Hands-on leadership - you write code, review PRs, set the bar. You also know when to step back.
• Comfortable with ambiguity and the pace of a zero-to-one build.

• Background in network security, asset discovery, or traffic analysis
• Familiarity with OT/ICS network protocols (Modbus, S7comm, PROFINET, DNP3)
• Multi-agent architectures in production (A2A, agent swarms).
• Memory libraries (Mem0, LangMem, MemGPT).
• LLM evaluation frameworks (LangSmith, Bedrock Evaluations).
• Vector stores (Pinecone, Weaviate, Chroma), PostgreSQL/MongoDB.
• Background in cybersecurity or critical infrastructure.
• IaC (CDK, Terraform).