Member of Technical Staff: Research
About the role
Engineer role focused on building agents and training models for memory retrieval and context management at enterprise scale. Reports to the founder; joining a small, distributed team to develop production-grade retrieval, memory extraction, and agent-based systems.
Responsibilities
- Build agents that improve retrieval: query understanding, ranking, and what to pull into context.
- Finetune the models that extract, update, and consolidate memory on Zep's domain.
- Finetune the models that power those agents, so the retrieval loop and the agent get better together.
- Own the work from dataset creation through experiment design, evaluation, training, and a change that ships to production. Our engineers work the serving path alongside you.
- Build the eval harnesses that catch regressions in retrieval, memory quality, and agent task completion before a release ships.
- Write up what you find, including the results that killed an idea, so the rest of engineering can build on it.
Qualifications
- You have shipped production ranking, retrieval, or query understanding.
- You've built classical ML into a real product — logistic regression, SVMs, GBTs, single-layer perceptrons.
- You've shipped finetuned models to production. You know transformer architectures and training workflows, and you work in PyTorch.
- You have shipped a non-trivial agentic system to production. Not a prototype, not a thin wrapper over a chat-completion API.
- You have a research methodology: dataset creation and curation, experiment design, and evaluation. You can frame an open problem and design an experiment that answers it.
- You have built evaluation for retrieval, generation, or agent tasks: gold sets, offline metrics, online tests.
- You write strong Python, and you have enough production AWS to ship, monitor, and iterate on what you train.
- You have a Master’s in Computer Science or equivalent experience.
Skills
About Zep AI
The Memory Foundation For Your AI Stack
Build AI assistants that continually learn and delight users with personalized and accurate experiences. ## Memory that learns from your users Zep intelligently learns from user interactions, improving your assistant or agent's knowledge over time. Recall user facts in milliseconds, with Zep adding no latency to your prompt creation. ## Ready for Production and Scale - Granular Memory Controls: Go beyond semantic search with developer-defined rubrics for user fact relevance. - Comprehensive APIs and SDKs: Python, TypeScript, and Go SDKs, with full CRUD control of stored facts. - SOC 2 and tools for Privacy Compliance. ## Build Consistent and Correct LLM Apps Zep's Structured Output and Dialog Classification tools build on Zep's memory enabling you to build more accurate and consistent user experiences. - Extract strongly-typed data from chat history, quickly & accurately: Go beyond your LLM provider's JSON or Structured Output mode with built-in types for datetimes, floats, emails, RegEx patterns, and more. - Instantly classify conversation state: Understand user intent and emotion, segment users, and more.
More open roles at Zep AI
- Head of Forward Deployed Engineering2mo agoHybrid (San Francisco, CA / Remote (US))