Applied AI Engineer

Accrescent Group; San Francisco (CA); On-site; USD 140,000 - 220,000; Full time

Job summary

Accrescent Group is seeking an Applied AI Engineer to build and maintain production-grade agent infrastructure at an early-stage company. This role focuses on developing reliable agent systems that execute tasks across iterations, retain long-term context, recover from failures, and include human oversight when needed.

You will own the agentic infrastructure, ship to production in weeks, and define how agents plan, remember, fail, and recover.

Qualifications

• Shipped LLM agents that ran unattended in production for real users.
• Built eval harnesses that people actually used to make shipping decisions.
• Experience with retrieval and memory systems that work on real, messy operational data.

Responsibilities

• Build and maintain the core infrastructure that enables agents to execute tasks reliably, even after dozens of iterations.
• Design and implement memory systems that retain months of client context from messy operational data.
• Develop eval harnesses that teams actually trust to decide what ships to production.
• Own the full loop: build it, measure it, break it, fix it, and make it learn.
• Ship agent systems for real customers and iterate based on production feedback.
• Handle whatever needs doing, infrastructure, orchestration, customer collaboration, and hiring.

Skills

Python

LLM agents in production

Memory systems

Retrieval augmented

Agent orchestration

Infrastructure

Job description

We're seeking an Applied AI Engineer to build and maintain production-grade AI agent infrastructure at an early-stage company. This role focuses on developing reliable agent systems that execute tasks across multiple iterations, retain long-term context, recover from failures, and involve human oversight when needed. The ideal candidate has shipped LLM agents to production, built reliable evaluation frameworks, and developed retrieval and memory systems using real-world operational data.

Job Description:

About the Role

You'll own the agentic infrastructure at the company, the systems that let agents execute reliably, remember context over months, and know when to pull in a human. While everyone is building agents, almost nobody builds agents that actually run in production at scale. You'll ship to production in your first week and decide how agents plan, remember, fail, and recover.

What You'll Do:

• Build and maintain the core infrastructure that enables agents to execute tasks reliably, even after dozens of iterations.
• Design and implement memory systems that retain months of client context from messy operational data.
• Develop eval harnesses that teams actually trust to decide what ships to production.
• Own the full loop: build it, measure it, break it, fix it, and make it learn.
• Ship agent systems for real customers and iterate based on production feedback.
• Handle whatever needs doing, infrastructure, orchestration, customer collaboration, and hiring.

What We're Looking For:

• Shipped LLM agents that ran unattended in production for real users; you understand that the model is the easy part.
• Built eval harnesses that people actually used to make shipping decisions.
• Experience with retrieval and memory systems that work on real, messy operational data rather than demo datasets.
• Strong Python proficiency and hands-on experience with agent orchestration and infrastructure.
• Track record of intensity and execution, you force things into existence; bonus if you've built agent tooling in the open or founded something.

Skills and Certifications [note: bold skills and certification are required]

Python