Principal Engineer & Architect - AI Agent Plaform

The role

You will be the senior-most engineer and technical architect for the platform. You will design integrations, data layers, APIs, infrastructure, security models, and AI agents.

What you will do

• Design how client systems connect, data is normalized, and information is served to dashboards and agents.
• Build primary framework skeletons.
• Handle agent design, tool usage, guardrails, evaluations, and monitoring.
• Lead deployment architecture, CI/CD, observability, and cost management.
• Own tenant isolation, secrets management, least-privilege access, and audit trails.
• Set code standards and conduct reviews.
• Guide a distributed bench of senior engineers through written specifications.
• Serve as the technical point of contact with clients and design partners.

Required qualifications

• 8+ years of production software experience, including recent hands-on ownership of a major system's architecture.
• Deep experience in TypeScript and Node.js ecosystems.
• Experience with modern frontends (React, Remix / React Router v8, Tailwind, ShadCN).
• Experience with relational ORMs (Drizzle), validation tools (Zod), databases (PostgreSQL, Redis), and queueing systems (PgBoss).
• Proven track record shipping and operating real LLM agent systems.
• Experience building guardrails, evaluating agents, monitoring them in production, and handling agent-specific failure modes.
• Deep understanding of RAG pipelines, chunking strategies, and vector data workflows.
• Experience managing uptime, running CI/CD, setting up observability, and handling production incidents end to end.
• Proven experience making and defending decisions around platform hosting and runtimes using AWS or GCP.
• Experience with complex third-party API environments involving webhooks, incremental polling, idempotency, retries, data normalization, and data reconciliation.
• Strong experience with relational and event-driven data designs.
• Practical experience with multi-tenant SaaS security, tenant isolation, secrets hygiene, least-privilege access control, and audit logs.

Nice to have

• Official AWS or GCP Cloud Architect certifications.
• Experience with agent frameworks beyond single-vendor stacks (such as OpenClaw, MCP, or A2A).
• Experience with Infrastructure as Code and observability tools like Prometheus or Grafana.
• Background in graph databases and knowledge graphs.
• Early-stage startup experience building new product lines from 0→1.

About the company

DevSavant builds and operates managed AI agents and AI coworkers that run real business workflows in production for SaaS companies.