Own the design and evaluation of Hercules' AI coding agent to enhance its efficiency and accuracy.
Posted by employer 1 month ago
First seen on Joblaze 1 month ago
Last verified on the company career page 15 hours ago
Skills & Technologies
What you'll build
Must have
Practical constraints
AI in the day-to-day
Leverage user data and code repositories to guide experimentation for the AI coding agent.
Not disclosed in this posting: years of experience, visa sponsorship.
Benefits
Joblaze summary
In this role, the Staff Technical Product Manager will focus on enhancing Hercules' AI coding agent by improving its efficiency and accuracy through a comprehensive system design. Candidates should possess strong technical skills in software development, system architecture, and AI context engineering, with a solid grasp of the latest best practices in the field. This position is ideal for experienced product managers who have a background in AI and a keen understanding of user experience design. Hercules emphasizes a fast-paced, excellence-driven work environment, encouraging rapid iteration and a commitment to quality.
Joblaze insights
Quick facts
From the original posting
What are we looking for?
Hercules is looking for a senior or staff level product manager to own our AI coding agent.
What will you do?
Your #1 and only goal is to make Hercules' AI coding agent cheaper, faster, and more accurate (our pareto frontier)
You will own Hercules' online evals and offline evals. We believe evals are mission critical to our success and so explicitly require someone with experience building out technical evals
You will own Hercules' entire context/harness system design (which includes system prompt, tools, memory, skills, summarization/compression, hooks, codebase design etc)
You will leverage our 100k+ users, 200k+ code repos, and millions of chat threads to guide your experimentation.
We expect candidates to be incredibly strong across all of the following areas:
Software fundamentals: You are building an AI coding agent. We expect you to be technical and able to code. We expect you to have a decent understanding of system design, architecture, data modeling, and API design. In saying this, you will work with an engineering counterpart to work on complex implementation
Product sense: strong intuition for the goals customers are trying to achieve and novel solutions to help them achieve them
Design sense: Track record of building simple, delightful UX/UI that makes it easy for customers to achieve their goals
AI context and harness engineering: strong experience with the most up to date context and harness engineering best practices like summarization/compression, prompting, prompt caching, subagents, memory, context management, tools, async tools, deferred tools, skills, etc
Yes, we know this industry is evolving rapidly and the "best practices" change every week, but yes, we are still actively 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, (some sort of agent framework like AI SDK), (some sort of eval platform like LangSmith)
AI: able to truly 10x your workflow by being on 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
We ship. We ship fast, iterate, and correct mistakes quickly. Our bias for action speeds up our learning and delights our customers.
What are Hercules’ benefits?
Unlimited AI token budget
Take what you need vacation policy
Healthcare, vision, and dental
What’s the compensation?
$100k-$250k + equity (variable based on seniority, equity, and location)
Standard company text repeated across Hercules's postings is omitted here.