Agentic Infrastructure Engineer — Frontier AI Lab

Aionia Group; New York (NY); On-site; USD 250,000 - 500,000; Full time

Benefits offered by this job

Competitive equity

On-site collaboration with a small team

High compensation package

Job summary

Aionia Group is seeking an Agentic Infrastructure Engineer to design the infrastructure layer that supports intelligent systems in New York, NY. You will enhance system reliability, safety, and effective orchestration of AI capabilities.

Your role involves building core runtime systems, developing robust control-plane logic, and ensuring optimal agent performance. This unique position blends research with practical application, working within a small elite team dedicated to pushing the frontiers of AI technology.

Qualifications

• 3–15 years of backend or distributed systems engineering experience.
• Proven track record of improving system reliability, performance, and observability.
• Experience owning systems end-to-end from design to iteration.

Responsibilities

• Design and build agent harnesses for different product experiences.
• Build core runtime systems including execution frameworks.
• Develop control‑plane logic for routing and planning.

Skills

Distributed systems engineering

Backend platforms

Observability

Performance improvement

Tools

Python

Go

Scala

Temporal

Cloudflare

Envoy

Job description

Frontier AI Lab · Confidential · SF or NYC

Agentic Infrastructure Engineer

Aionia is sourcing for a small number of confidential roles at frontier AI labs building at the boundary of what intelligent systems can do. This is not an application layer role. You will own the execution layer — the runtime infrastructure that determines how agents reason, act, fail, recover, and improve in production.

What You’ll Build

• Design and build agent harnesses that power different product and research experiences
• Build core runtime systems including execution frameworks and multi-model orchestration
• Develop control‑plane logic for routing, planning, and tool invocation with strong safety guarantees
• Optimize agent systems for latency, reliability, and production correctness
• Analyze real‑world failures and use data to drive iterative improvements
• Build and operate online experimentation and offline evaluation frameworks
• Improve observability, testing, and simulation systems for safe, measurable progress
• Create sandboxed environments where agents can act and self‑validate safely
• Continuously adapt orchestration systems as model capabilities evolve

Stack & Tools

Python, Go, Scala, Temporal, Modal, Cloudflare, Envoy, Distributed Systems, Agent Orchestration

Requirements

Must‑Have — Non‑Negotiable

• Strong experience building distributed systems or backend platforms in production environments
• A track record of improving system reliability, performance, and observability under real-world pressure
• Experience owning systems end-to-end — from design through production and iteration

Required

• Comfort working in ambiguous, fast‑moving environments with rapid iteration cycles
• Familiarity with experimentation, evaluation, or data‑driven product improvement loops
• Ability to debug complex systems and identify root causes of failures — not just symptoms
• 3–15 years of backend or distributed systems engineering experience

Even Better If

• You’ve built or worked on agent harnesses, orchestration layers, or execution frameworks
• You think in terms of control planes, feedback loops, and system-level optimization — not just features
• You’re excited about diagnosing failure modes and iterating toward measurable improvements
• You care deeply about production quality — not just making systems work, but making them reliable, safe, and scalable
• You’re motivated by pushing the frontier of how intelligent systems behave in the real world

Why This Role Is Different

• You’re building the layer that makes AI reliable. Not above the model — around it. The execution layer is where reliability, safety, and capability actually meet.
• Research meets production. You’ll work directly alongside researchers and translate model capabilities into trustworthy systems that operate at scale.
• Small team, outsized impact. Every architectural decision you make shapes how intelligent systems behave in the world.
• The mission is the point. This lab exists to get superintelligence right. If that drives you, there is no comparable environment.

Compensation

$250,000 – $500,000+ total compensation depending on level, with competitive equity at an organization of this caliber.

Top‑of‑Market Base Meaningful Equity SF or NYC · On‑Site Small Elite Team