Product Engineer, Agents & Harnesses
Engram · San Francisco
About this role
## About Engram Today’s AI is a brilliant stranger: it can solve the world’s hardest math problems, but it knows next to nothing about you and your work. It rereads your files to answer even basic questions, burns an enormous amount of tokens when sifting through large corpuses, and between sessions, it retains scraps at best. Engram trains models to study your world and anticipate your questions in advance—forming **engrams**, compact memories that capture your knowledge and history. The more we study your context at training time, the better we become at inference time. Engram is already working with leaders in AI like **Microsoft, Notion, and Harvey**, and recently raised **$98M**. --- ## About the Role (Product Engineer — Agents & Harnesses) Engram trains models on the knowledge and context that make each customer’s work unique. Making that useful in practice means understanding customer workflows and solving the last-mile problems that arise when our systems meet real data, code, and users. You’ll work closely with researchers and customers to **build, evaluate, and deploy agents** that use Engram. You’ll explore how models behave in real-world environments and solve deployment challenges yourself—then turn successful deployments into repeatable approaches and a playbook to help 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 Engram systems. - Own customer issues through resolution: diagnose failures, implement and ship fixes, and verify they work in the customer’s environment. - Build evaluations to measure **quality, latency, and cost**, and use results to improve deployments. - Package successful approaches into reusable agent integrations, evaluation tools, and deployment playbooks. --- ## Your Background - 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**, including context management, tool use, and evaluation. - Strong production coding skills (APIs, data integrations, reliable backend systems). - Ability to debug unfamiliar codebases and trace failures across data, models, and application code. - Track record of owning problems end-to-end: discovery → implementation → deployment → validation with users. - Clear communication with customers and researchers; can translate ambiguous problems into actionable strategy. - Comfort with ambiguity and high ownership in an early-stage company. --- ## Bonus Points - Experience in forward-deployed or customer-facing engineering. - 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. --- ## Location & Hiring Notes - Based in **San Francisco**. - This role is **in-person** in the SF office. - Competitive c
Listing freshness
CronJobs last confirmed this listing 2h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.