Applied AI Engineer

Harrison Clarke; San Francisco (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

Harrison Clarke is partnering with a well-funded early-stage AI startup to build production AI systems. This isn’t a research lab, but an opportunity to build, ship, and own AI products that customers use daily.

You’ll work across LLMs, agents, retrieval, infrastructure, and product engineering, taking ideas from prototype to production while helping define the future technical direction of the company. You'll be one of the earliest AI engineers, working directly with the founders on core

Qualifications

• Experience building AI agents, copilots, or workflow automation systems.
• Proficiency in prompt engineering, RAG, tool calling, and agent frameworks.
• Proficiency in Python and modern AI frameworks.
• Experience working with APIs, distributed systems, and cloud infrastructure.
• Experience deploying and monitoring production AI applications.

Responsibilities

• Build production AI applications powered by LLMs and AI systems.
• Develop AI agents capable of reasoning, planning, and executing complex workflows.
• Design and implement retrieval, memory, and evaluation systems for AI products.
• Take ideas from prototype to production and help shape product direction.
• Collaborate on internal tooling and infrastructure to support rapid experimentation.

Skills

AI agents

Prompt engineering

Python

APIs

Distributed systems

Production deployment

Job description

We're partnered with a well-funded early-stage AI startup building production AI systems that solve real-world problems at scale.\\

This isn't a research lab.

This is an opportunity to build, ship, and own AI products that customers use every day. You'll work across LLMs, agents, retrieval, infrastructure, and product engineering, taking ideas from prototype to production while helping define the future technical direction of the company.

You'll be one of the earliest AI engineers, working directly with the founders on core product and platform development.

What you'll build

• Production AI applications powered by modern LLMs
• AI agents capable of reasoning, planning, and executing complex workflows
• Retrieval, memory, and evaluation systems
• End-to-end AI products from prototype through production
• Internal tooling and infrastructure supporting rapid experimentation
• Scalable AI services deployed to real customers

You'll likely have experience with

• Building AI agents, copilots, or workflow automation systems
• Prompt engineering, RAG, tool calling, and agent frameworks
• Python and modern AI frameworks
• Working with APIs, distributed systems, and cloud infrastructure
• Deploying and monitoring production AI applications
• Moving quickly in high-ownership startup environments

Nice to have

• Fine-tuning or post-training experience
• AI evaluation frameworks and observability
• Inference optimization or model serving
• Early-stage startup or founding engineer experience
• Founding-level ownership with meaningful technical influence
• Work directly alongside experienced founders
• Build products that reach users rather than internal research projects
• Solve challenging problems across AI, product, and infrastructure
• High autonomy, rapid iteration, and the opportunity to shape both the engineering culture and technical roadmap
• Competitive compensation and meaningful early-stage equity