Senior AI Systems Engineer – Agent Execution & Orchestration

Stott and May; Los Angeles (CA); On-site; USD 170,000 - 220,000; Full time

Job summary

A fast-growing AI company in Los Angeles is seeking a Senior AI Systems Engineer to develop agent execution systems that interact with real infrastructure. The candidate should have strong backend experience, particularly in TypeScript and Python, and experience building production-level LLM systems. Responsibilities include designing architectures for memory and retrieval, ensuring reliability, and facilitating workflow automation. This opportunity allows you to work with a small, expert team pushing the boundaries of AI in high-impact environments.

Qualifications

• Strong backend or distributed systems experience.
• Experience building LLM-powered systems in production.
• Experience with agentic systems or workflow automation.

Responsibilities

• Build and operate agent execution systems.
• Design retrieval and memory architectures.
• Build tool-calling frameworks for safe interactions.

Skills

TypeScript

Python

Distributed systems

Reliability

Observability

Docker

Kubernetes

Workflow automation

Job description

Senior AI Systems Engineer – Agentic Platforms

$170k–$220k + Equity

A fast-growing, venture-backed AI company is hiring engineers to build systems where AI doesn’t just generate outputs, but executes real workflows across infrastructure.

The team is building autonomous agents that operate in production environments, interacting with real systems, permissions, and failure modes, not just APIs or demos.

The role

• Build and operate agent execution systems (task loops, scheduling, control planes)
• Design retrieval and memory architectures for long-term, structured context
• Build tool-calling frameworks that safely interact with external and enterprise systems
• Design systems for observability, failure handling, and recovery in production AI systems
• Work on distributed, production-grade infrastructure powering agent workflows

Requirements

• Strong backend or distributed systems experience (TypeScript required, Python preferred)
• Experience building LLM-powered systems in production, not prototypes
• Experience with agentic systems, orchestration, or workflow automation
• Strong understanding of reliability, observability, and failure modes in production systems
• Experience with Docker/Kubernetes or production infrastructure
• Bonus: experience in DevOps, SecOps, or infrastructure automation

This is an opportunity to join a small, highly technical team building agent infrastructure at the edge of what’s possible, where the focus is on real systems, real constraints, and real production impact.