AI Engineer (II/Senior)

About us

ArrePath is a fully remote startup using AI to discover new classes of oral small-molecule drugs. We work in antibacterials, mycobacterial lung disease, immunology, and inflammation. Our platform has found inhibitors of six new antibacterial targets. Our team has helped discover, develop, or obtain approval for nine antibiotics. Our investors include Insight Partners, Innospark Ventures, and the Boehringer Ingelheim Venture Fund.

Ariadne is our AI scientific assistant. It is an agent with persistent memory, a web chat interface, and a single MCP gateway that brokers access to compute on AWS (Batch, Lambda, S3), external scientific APIs, and our internal data. It also includes a multi-stage literature search pipeline and an evaluation harness for measuring agent behavior. It gives our scientists natural-language access to more than 30 machine-learning models and cheminformatics tools. They use it to run computational chemistry workflows, search the scientific and patent literature, query internal assay data, and analyze results in conversation multiple times per day.

The role

We’re hiring an engineer to be the second developer on Ariadne. You’ll work directly with Kurt Thorn, our CTO, who leads Ariadne development, and with the scientists who use it every day. ArrePath is a small company, so you’ll get direct exposure to the leadership team.

On a two-person team you own work end to end. That means taking a bug report or feature request from a scientist, designing the change, building it with coding agents, validating it, and shipping it to production. There’s no product manager, QA team, or separate ops group. You’ll be the person who decides how something should work and makes sure it does.

What you’ll work on

Your main focus will be making Ariadne more autonomous, reliable, and robust:

• Memory: what the agent retains across sessions, and how it retrieves and uses it
• File tracking: keeping track of the data files, results, and artifacts a scientist works with over a long project
• Reasoning: planning and staying on course through long, multi-step scientific tasks
• Tool execution: choosing the right tools, calling them correctly, and recovering when they fail
• Delegation: handing work off to sub-agents and combining what they return
• Web interface: improving the TypeScript and Vite chat app where it limits what scientists can do

The stack is Python, TypeScript, AWS, Docker, GitHub Actions, and LLMs from several providers via Amazon Bedrock.

How we work

Two humans and a fleet of coding agents build Ariadne. Most of our code is written by agents such as Claude Code and Codex, running in parallel. Our job is to direct them well and to be accountable for what ships.

In practice:

• Humans own design and judgment. Bounded changes get a short design review. Architectural changes get a written spec and an implementation plan before any code is written.
• Tests and evidence over assertions. We practice TDD for behavior and verify agent claims against real results.
• Written invariants. Component specs record the invariants that matter, and tooling checks code against them.
• Cross-model review. We use reviewers from different model families to stress-test designs and diffs.
• Repository rules agents follow. Our CLAUDE.md, skills, and hooks encode how work gets done, and we keep improving them.

You’ll help shape this process, not just follow it. If you’ve built your own agentic workflow and have opinions about what works, we want to hear them.

What we’re looking for

The essential qualification is experience on both sides of agentic software: building agentic systems and using agents to write code.

You have:

• Experience building agentic systems with LLMs: tool use, memory, planning, multi-agent delegation, evals, and the ways these systems fail
• Substantial hands-on experience using coding agents (Claude Code, Codex, Cursor, or similar) on a real codebase, not just demos
• The judgment to know when an agent’s output is wrong, the habit of checking, and the discipline to break work into pieces agents can do reliably
• 2+ years of professional Python or TypeScript experience
• Clear written communication. Much of the work is writing specs, reviews, and instructions for people and agents.
• Ability to get productive fast in a large existing codebase.

Nice to have:

• Background in chemistry, biology, or another scientific field
• Experience with MCP servers or retrieval and search systems
• Experience training ML models
• Experience at an early-stage startup

Logistics

Structure	Full-time (40 hours/week), salaried, at-will employee with benefits.
Compensation	$130,000–$170,000 per year, depending on qualifications, plus equity, health, dental, and vision insurance, and a 401(k)
Location	Fully remote, anywhere in the U.S. Applicants must be authorized to work in the U.S. without visa sponsorship, now or in the future.
Start	As soon as possible

To apply

Email [email protected] with your CV and a letter describing your experience with agentic development, building agents, or both. Links to GitHub repositories or other existing work are especially valuable.

Apply by email