Principal AI Platform Architect

MaintainX; United States; On-site; USD 180,000 - 320,000; Full time

Benefits offered by this job

Flexible time off

Equity opportunities

Training and development investments

Comprehensive healthcare coverage

Job summary

MaintainX is seeking a Principal Engineer to own the AI platform's technical vision and scale it to meet ambitious goals. You will lead architecture, set direction across divisions, and drive governance and reliability for agent, skill, and tool ecosystems.

You will define architecture, scale context graphs, and build the developer experience while shaping evaluation and observability. A track record of leadership and backend excellence is essential.

Qualifications

• Strong Python backend expertise with experience designing APIs, services and data pipelines.
• 3+ years building ML/LLM-powered systems in production with evaluation, latency, cost and reliability.
• 10+ years of software engineering with backend systems, distributed architecture or platform infra.
• Production agentic systems: multi-agent orchestration and tool use.
• Experience with MCP, LangGraph, LlamaIndex, and evaluation/observability platforms is a plus.

Responsibilities

• Define the Agent/Skill/Tool architecture and evolve the platform for discovery and governance.
• Scale the context graph and knowledge systems to turn vast manuals and data into intelligent insights.
• Own developer experience including agent orchestration and observability.
• Design offline/online evaluation loops to improve agent performance from user interactions.
• Drive cross-division alignment and represent engineering externally.

Skills

Python backend

Architecture leadership

ML/LLM systems

Distributed systems

APIs design

Tools

LangGraph

LangSmith

Langfuse

BraintrustRAG pipelines

vector databases

Job description

MaintainX is seeking a Principal Engineer to own the AI platform's technical vision and scale it to meet ambitious goals. You will lead architecture, set direction across divisions, and drive governance and reliability for agent, skill, and tool ecosystems.

You will define architecture, scale context graphs, and build the developer experience while shaping evaluation and observability. A track record of leadership and backend excellence is essential.