Product Engineer, Agents & Harnesses

Engram Lab•San Francisco, CA

8h•Onsite

About The Position

Engram trains models on the knowledge and context that make each customer’s work unique. The Product Engineer, Agents & Harnesses works closely with researchers and customers to build, evaluate, and deploy agents that use Engram. The role explores how models behave in real-world environments and solves last-mile deployment problems involving real data, code, and users. Successful deployments are turned into repeatable approaches and playbooks to help Engram reach more customers. The position is based in Engram’s San Francisco office and is in-person. Engram offers competitive cash compensation and startup equity.

Requirements

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, including 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 with customers and researchers, including the ability to 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 lasting solutions.

Nice To Haves

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 taken from idea to real users.

Responsibilities

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 successful deployments.
Develop evaluations with researchers and customers to identify where agents succeed or fail and what changes improve performance.
Build integrations and solve last-mile deployment problems across customer data, application code, and Engram’s systems.
Own customer issues through resolution by diagnosing failures, implementing and shipping fixes, and verifying them in the customer’s environment.
Build evaluations with customers to measure quality, latency, and cost, and use results to improve deployments alongside researchers and engineers.
Package successful approaches into reusable agent integrations, evaluation tools, and deployment playbooks that support Engram’s distribution.