AI Context & Harness Engineer

Hercules; United States; Hybrid; USD 100,000 - 250,000; Full time

Benefits offered by this job

Equity

Job summary

Hercules is seeking a senior or staff level AI Context & Harness engineer to help us build the future of AI software development. You will own Hercules' AI coding agent and drive its ongoing improvement. We value strong software design, clean code, and a track record of shipping features to customers.

Our stack includes TypeScript, React, Postgres, Redis, Docker, and Temporal. This role blends hands-on development with research in a fast-paced environment; in-office in San Francisco is

Qualifications

• Experience designing scalable AI-powered software.
• Strong code quality and monorepo work.
• Proven track record shipping many features to customers.
• Deep experience with context and harness engineering practices.

Responsibilities

• Build, maintain, and own Hercules' AI coding agent.
• Build, maintain, and own Hercules' online evals and offline evals.
• Research novel ways to reduce cost, speed up, and improve accuracy using 200k+ repos and millions of chat messages.

Skills

Software design

Code quality

Shipping features

Context & harness engineering

System design

Monorepos

Prompting/Memory/Tools

Async tools/Deferred tools

Tools

TypeScript

React

PostgreSQL

Redis

Docker

Temporal

CDK/Terraform

Drizzle ORM

ClickHouse

Job description

Hercules is looking for a senior or staff level AI Context & Harness engineer to help us build the future of AI software development.

What will you do?

• Build, maintain, and own Hercules' AI coding agent.
• Build, maintain, and own Hercules' online evals and offline evals.
• Research novel ways to make our agent cheaper, faster, and more accurate (you will have access to 200k+ repos and millions of chat messages).

What skills do we expect you to have?

• Software fundamentals: system design, architecture, data modeling, and API design.
• Code and codebase quality: write clean, maintainable code; work effectively in monorepos.
• Product/design sense: track record of independently shipping many features to customers.
• Context and harness engineering: strong experience with up-to-date best practices such as summarization/compression, prompting, prompt caching, subagents, memory, context management, tools, async tools, deferred tools, RAG, skills, etc.
  • We know this industry evolves rapidly, but we are looking for someone who has wrestled with these challenges at scale and has strong opinions about what works and what doesn't.
• Our core stack: TypeScript, React, containers, Postgres, Redis, and Temporal.
• AI coding: able to truly 10x your workflow by being on the frontier of AI coding.

What’s Hercules’ stack?

• Technologies: TypeScript, React, AI SDK, Postgres, Redis, Clickhouse, Tailwind, IaC (CDK, Terraform), Docker, Otel, Hono, Drizzle ORM, Temporal.
• Clouds: Cloudflare, AWS.
• AI Models: OpenAI, Anthropic, Google.

What are Hercules’ operating principles?

• We ship fast, iterate, and correct mistakes quickly; our bias for action speeds up learning and delights customers.
• We strive for excellence. Doing things well is in our DNA; we get the details right and produce exceptionally simple, self‑serve outputs.
• We are hungry. We work hard, break through walls, and are willing to operate at any level to get things done.

Is Hercules in‑office or remote?

The founding team works in‑office in San Francisco (Kearny and Bush). We have a strong preference for in‑office but are open to remote for exceptional candidates willing to work in US time zones and travel to the office regularly.

What are Hercules’ benefits?

• Unlimited AI token budget.
• Take what you need vacation policy.
• Healthcare, vision, and dental.
• Daily lunches, dinners, and snacks in the office.
• We guarantee you will do the best work of your career here.

What’s the compensation?

$100k–$250k + equity (variable based on seniority, equity, and location).