You and the process

With a person
Anna, in-house recruiter
9 years hiring engineers
30 minutes with a real recruiter
They read your CV with you, on a call, and say where the offers are being lost.
Didn’t find what you were looking for? Tell us what to build
Engram

Product Engineer, Agents & Harnesses

  • Office

Salary

Not stated

Similar roles pay $145K - 235K a year · our estimate

AI summary

For members

The whole posting in a few lines. Sign up to read it here and on every role you open.

Sign Up to Read

Description

The company trains AI models on each customer's own knowledge and context, so they can answer questions about that work without rereading files from scratch, use fewer tokens on large document sets, and keep memory between sessions.

Its method is to have models study a customer's world ahead of time and build compact memories of that knowledge and history, called engrams. Studying more context during training improves results at inference time.

The company already works with Microsoft, Notion, and Harvey, and has raised $98M from General Catalyst, Kleiner Perkins, Sequoia, Factory, Modern, Amplify, Neo, and others. Investors and advisors include Assaf Rappaport, Andrej Karpathy, and Pieter Abbeel.

The role centers on taking that customer context and making it work in practice, which means learning how each customer works and fixing the last-mile issues that appear when the systems meet real data, code, and users.

This is a Product Engineer role focused on agents and harnesses. You will work with researchers and customers to build, test, and ship agents that run on the company, study how the models behave in real environments, and handle last-mile deployment work yourself. You will also turn deployments that succeed into repeatable methods and a playbook for reaching more customers.

Responsibilities

  • Prototype and test workflows built on the company with the research team.
  • Work with customers directly to learn their workflows, find where the company fits, and agree on what a successful deployment looks like.
  • Build evaluations with researchers and customers to find where agents succeed or fail and which changes help.
  • Build integrations and handle last-mile deployment across customer data, application code, and the company's systems.
  • Take customer issues to resolution: diagnose failures, build and ship the fixes, and confirm they work in the customer's environment.
  • Build evaluations with customers that measure quality, latency, and cost, and use the results to improve deployments with researchers and engineers.
  • Turn approaches that work into reusable agent integrations, evaluation tools, and deployment playbooks that help the company reach customers.

Requirements

  • A bachelor's degree in computer science, engineering, machine learning, or a related field, or equivalent practical experience.
  • Experience building and shipping LLM applications or agents, including context management, tool use, and evaluation.
  • Strong production coding skills, including building APIs, data integrations, and reliable backend systems.
  • Ability to work through unfamiliar codebases and trace failures across data, models, and application code.
  • A record of carrying a problem from discovery through implementation, deployment, and validation with users.
  • Clear communication with customers and researchers, able to turn unclear problems into concrete strategy and solutions.
  • Comfort with ambiguity and high ownership at an early-stage company, with the judgment to move fast and still build solutions that last.
  • Nice to have: experience in a forward-deployed or customer-facing engineering role.
  • Nice to have: experience building agent systems, retrieval pipelines, or evaluation frameworks for real-world workflows.
  • Nice to have: experience fine-tuning language models or working with researchers to get model improvements into production.
  • Nice to have: experience as a founder or early engineer, or technical projects you have taken from idea to real users.

Conditions

The role is based in the San Francisco office and is fully in person.

The company is an equal opportunity employer and welcomes applicants of any race, color, religion, national origin, gender, gender identity, sexual orientation, age, disability, or veteran status.

Benefits

  • Competitive cash compensation.
  • Startup equity.

Where you’d work

From the office

The office

About the company

Engram

  • Industry: AI

Office in San Francisco, United States

Your chances

We've checked whether it's still hiring and how crowded it is.

  • 18 checks run
  • 0 red flags

Still hiring?

12 checks

No red flags

How crowded?

6 checks

No red flags

Fits Me

How well does this role fit you?

Answer a few questions or drop your CV, and every role gets a fit score with the reasons, this one first.

  • Your field
  • Level
  • Stack
  • Work model
  • Salary floor
  • Must-haves
Details11 facts · Role, Location, Compensation, Employment, Company
Tech stack
  • LLMs
Type
Full-time
Equity
Equity offered
Industry
AI
Specialty
Backend
Region
United States
Show 5 more factsShow less

Role

Category
Development
Specialty
Backend
Tech stack
  • LLMs

Location

Work model
Office
Region
United States
Office
  • San Francisco, United States

Compensation

Salary
Salary by agreement
Pay period
Annual
Equity
Equity offered

Employment

Type
Full-time

Company

Industry
AI

Something wrong with this vacancy?

Similar vacancies

Share this vacancy

What's wrong with it?

The employer never sees who reported.

Reason