Research Engineer San Francisco

Greptile; San Francisco (CA); On-site; USD 180,000 - 280,000; Full time

Benefits offered by this job

Relocation assistance up to $25K

Equity options

Job summary

Greptile is hiring a Research Engineer to advance AI-powered code review. You will work on agents and language models to push product capabilities, designing multi-agent systems for code validation and evaluation.

The team emphasizes research-led development and rapid iteration within a high-growth environment. You will collaborate with a dense, expert team and contribute to experimentation that scales to thousands of developers relying on Greptile.

Qualifications

• B.S. in Computer Science or an equivalent field is required.
• Candidates should have strong programming skills and research experience.
• Bonus: ML research with language models, papers at top conferences preferred.

Responsibilities

• Experiment with latest advances in agents and LLMs to improve product performance.
• Design and build multi-agent systems, harnesses, models, and evals for code validation.
• Prototype multi-agent code review workflows and help integrate successful prototypes into production.
• Stay updated on research in LLMs, information retrieval, and developer tooling.

Skills

Programming skills

Research experience

ML knowledge

Language models

Education

B.S. in Computer Science or equivalent

Job description

$180K – $280K • $75K – $150K Equity • Up to $25K in relocation assistance

Research Engineer

Greptile is an AI code reviewer that catches bugs and anti-patterns in pull requests with complete context of the codebase. Hundreds of top software companies, from YC startups to big tech, and teams in finance, healthcare, and defense, use Greptile to merge PRs faster and catch more bugs.

Greptile reviews 5B lines of code every month for 9,000+ customers. A new repo starts using Greptile every 2 minutes. We also uniquely offer self-hosted, air-gapped deployments for enterprises across defense, financial services, and healthcare.

We care more about hiring great people than filling specific slots, and everyone here wears multiple hats. The day-to-day for any given person tends to span more than one area.

Problems we’re excited about

• Coding standards can be idiosyncratic and are often poorly documented; can we build agents that learn them through osmosis like a new hire might?
• Can we identify for each customer what types of PR feedback they do and don’t care about, perhaps using some sample efficient RL, in order to increase signal-to-noise ratio?
• Some bugs are best caught by running the code, potentially against discerning AI-generated E2E tests. Can we autonomously deploy feature branches and use agents to parallel try to break the application to detect bugs?

Trajectory

• 9,000+ customers
• 5B lines of code reviewed every month
• Scaled from $0 to eight figures in ARR
• Raised $30M from Benchmark, Y Combinator, Paul Graham, and Initialized

Team

• We have assembled a small, talent dense team who have scaled critical functions at companies like Stripe, Google, Figma, etc.

Responsibilities

• Experiment with and apply the latest advances in agents and language models to push the performance and capabilities of our products
• Design and build the multi-agent systems, harnesses, models, and evals that power code validation
• Example: you might study multi-agent architectures, prototype and evaluate a multi-agent code review workflow, and then work with a team to integrate successful prototypes into production systems
• Stay on top of the latest research across LLMs, information retrieval, and developer tooling

Qualifications

• B.S. in Computer Science or equivalent
• Research experience in math, computer science, or physics
• Strong programming skills and sharp product intuition
• Bonus: research experience with ML, language models, or agents; papers accepted at top ML conferences; your own harnesses and evals for technical applications; experience post-training models; or a research master’s or PhD

You’ll like working here if

• You want to work on a product that thousands of developers rely on
• The chaos of high growth and things breaking is exciting to you
• You like being in an office every day around other smart people building hard things
• You love solving hard problems and shipping things that real users feel
• You’re AI-enthusiastic, you hack on side projects, you write a blog (technical or not), and you’re excited about what you’re building.

How to apply

• If this sounds like you, send an email to [e-mail] with your reasons why.