Founding ML Engineer – Search & Agents

Investment profile

Seed-stage company (<10) in San Francisco building vertical AI for physical science R&D.

They’re building an AI-native system that helps scientists and engineers make faster, better decisions by unifying fragmented technical data and powering workflow-specific agents.

Team is highly technical and in-office 5 days/week, with strong early traction and enterprise design partners.

Why this role

This is a true 0→1 role owning the search and retrieval layer that everything else builds on.

Search quality and evaluation are first-order. If retrieval is wrong, the product is wrong.

What you’ll build

Own the core search and retrieval layer that powers LLM- and agent-driven workflows across messy, heterogeneous scientific and engineering data (documents, tables, reports, and other technical artifacts).

This is a hands-on role with clear decision authority. You’ll define retrieval, ranking, and evaluation end to end, ship systems into production, and iterate directly from real user feedback. Your work will be immediately visible in product behavior.

You’ll work closely with the founders and users to translate ambiguous workflows into robust systems.

What you’ll work on

• Core retrieval and ranking, including hybrid search
• Relevance evaluation, metrics, and iteration loops that make quality legible
• Query understanding and feedback signals
• RAG and multi-step retrieval pipelines that support reasoning workflows
• Agent integrations that depend on reliable retrieval
• Tradeoffs across relevance, latency, cost, and robustness
• Evolving early systems into durable, production-grade infrastructure

What they’re looking for

• Strong software engineering fundamentals and end-to-end ownership
• Deep production experience building and shipping search systems (retrieval, ranking, eval)
• Experience owning relevance and evaluation, not just prototypes
• Experience designing retrieval or agent behavior beyond API wiring
• Comfort across modeling, systems, and infrastructure
• High bar for correctness and quality in ambiguous domains

Strong signals

• Owned search or relevance for a real product used by demanding users
• Built evaluation frameworks that improved quality over time
• Shipped hybrid search or ranking systems at scale
• Worked in tight deploy → observe → iterate loops with real users

Level and experience

• Typically, 3+ years of industry experience, with 1+ years owning production search systems.

About Us

Greylock is an early-stage investor in hundreds of remarkable companies including Airbnb, LinkedIn, Dropbox, Workday, Cloudera, Facebook, Instagram, Roblox, Coinbase, Palo Alto Networks, among others. More can be found about us here: https://greylock.com/

How We Work

We are full-time, salaried employees of Greylock and provide free candidate referrals/introductions to our active investments. We will contact anyone who looks like a potential match--requesting to schedule a call with you immediately.

Due to the selective nature of this service and the volume of applicants we typically receive from our job postings, a follow-up email will not be sent until a match is identified with one of our investments.

Please note: We are not recruiting for any roles within Greylock at this time. This job posting is for direct employment with a startup in our portfolio.