Bachelor's degree or equivalent experience in computer science, engineering, machine learning, or related field.
Experience in building and deploying LLM applications or agents.
Strong production coding skills, particularly in APIs and backend systems.
Ability to debug unfamiliar codebases and trace failures across various components.
Proven track record of owning problems from discovery to validation with users.
Excellent communication skills for translating complex issues into actionable solutions.
Comfortable with ambiguity and high ownership in a startup environment.
Responsibilities
Prototype and evaluate workflows using Engram in collaboration with researchers.
Engage directly with customers to understand their workflows and define successful deployment criteria.
Develop evaluations to assess agent performance and identify areas for improvement.
Build integrations and address last-mile deployment challenges across customer data and application code.
Own customer issues from diagnosis to resolution, implementing fixes and verifying effectiveness.
Measure quality, latency, and cost of deployments, using insights to enhance performance.
Package successful strategies into reusable integrations and deployment playbooks.
Benefits
In-person role in San Francisco office.
Competitive cash compensation.
Startup equity opportunities.
Full Job Description
About the role
Engram trains models on the knowledge and context that make each customer's work unique. Making that useful in practice means understanding their workflows and solving the last-mile problems that arise when our systems meet real data, code, and users.
We're looking for a Product Engineer - Agents & Harnesses to work closely with our researchers and customers to build, evaluate, and deploy agents that use Engram. You'll explore how our models behave in real world environments, and solve last mile deployment problems yourself. You'll turn successful deployments into repeatable approaches and a playbook that help us reach more customers.
What you'll do
Work with researchers to prototype and evaluate workflows that use Engram.
Work directly with customers to understand their workflows, identify useful applications for Engram, and define what a successful deployment looks like.
Develop evaluations with researchers and customers to understand where agents succeed, where they fail, and what changes improve performance
Build integrations and solve last-mile deployment problems across customer data, application code, and our systems.
Own customer issues through resolution: diagnose failures, implement and ship fixes yourself, and verify that they work in the customer's environment.
Build evaluations with customers to measure quality, latency, and cost; use the results to improve deployments alongside our researchers and engineers.
Package successful approaches into reusable agent integrations, evaluation tools, and deployment playbooks that support Engram's distribution.
Your background looks like
A bachelor's degree, or equivalent practical experience, in computer science, engineering, machine learning, or a related field.
Experience building and deploying LLM applications or agents, with an understanding of context management, tool use, and evaluation.
Strong production coding skills, with experience building APIs, data integrations, and reliable backend systems.
Comfort debugging unfamiliar codebases and tracing failures across data, models, and application code.
A track record of owning problems from discovery through implementation, deployment, and validation with users.
Clear communication, whether with customers or researchers - you can translate ambiguous problems into actionable strategy and solutions
Comfort with ambiguity and high ownership at an early-stage company, with the judgment to move quickly and build solutions that last.
Bonus points if you have
Experience in a forward-deployed or customer-facing engineering role.
Experience building agent systems, retrieval pipelines, or evaluation frameworks for real-world workflows.
Experience fine-tuning language models or working with researchers to bring model improvements into production.
Experience as a founder or early engineer, or technical projects you've taken from idea to real users.
Engram is based in San Francisco. This role is in-person in our SF office. We offer competitive cash compensation and startup equity.
