Principal System Engineer - Agentic AI

Discover International; United States; Hybrid; USD 180,000 - 300,000; Full time

Benefits offered by this job

Equity

Job summary

Discover International is seeking a Principal Engineer to define and build the architectural foundations of production-grade autonomous agent systems. This isn’t research or chatbots — it’s applied systems engineering at the frontier of AI-native development.

You’ll design agent execution frameworks, memory systems, and multi-model orchestration; build secure integrations and tool-calling pipelines for complex workflows; define reliability, observability, auditing, and recovery strategies; and

Qualifications

• Experienced building complex backend or distributed systems in production.
• Built AI-native or LLM-powered systems beyond prototypes.
• Demonstrate strong judgment in reliability, security, and long-term system evolution.
• Introduced abstractions or workflows that materially improved system scalability or engineering effectiveness.

Responsibilities

• Design agent execution frameworks, memory systems, and multi-model orchestration
• Build secure integrations and tool-calling pipelines for complex workflows
• Define reliability, observability, auditing, and recovery strategies
• Shape core platform primitives and long-term architectural patterns

Skills

Backend systems

Distributed systems

Reliability

Security

Job description

The next generation of software engineering is here. Autonomous agents are no longer prototypes — they’re running real workflows, managing infrastructure, and making critical decisions in production.

The challenges now are reliability, orchestration, memory, and security at scale.

We’re seeking a Principal Engineer to define and build the architectural foundations of production-grade autonomous agent systems. This isn’t research or chatbots — it’s applied systems engineering at the frontier of AI-native development.

What you’ll do:

• Design agent execution frameworks, memory systems, and multi-model orchestration
• Build secure integrations and tool-calling pipelines for complex workflows
• Define reliability, observability, auditing, and recovery strategies
• Shape core platform primitives and long‑term architectural patterns

Who you are:

• Experienced building complex backend or distributed systems in production
• Built AI‑native or LLM‑powered systems beyond prototypes
• Demonstrate strong judgment in reliability, security, and long‑term system evolution
• Introduced abstractions or workflows that materially improved system scalability or engineering effectiveness

Competitive base compensation + equity

Flexible location: remote / hybrid / major tech hubs

If designing the infrastructure for real‑world autonomous systems excites you, let’s connect!