AI Research Engineer (New York)
Edra · New York
About this role
## About Edra Edra is solving one of the hardest problems in enterprise AI: **AI models are generic, but company processes are specific**. We build **AI agents** that learn how processes actually run, and then execute their operations. We’re a **Series A startup**, backed by **Sequoia** and other leading VC firms, led by co-founders who created and led **Forward Deployed AI Engineering at Palantir**. We’re growing our team in **New York** and **London**—a deeply technical group of engineers, AI researchers, and strategists. ## The Role We’re building a **learning system** that teaches AI agents how enterprises actually work. Starting from what a customer already has—**knowledge base articles, support conversations, tickets, system logs, and agent traces**—we reverse-engineer how the business runs and write the process down as **inspectable instructions** that an agent can execute, with **confidence scoring** to determine when to automate vs. when to seek human input. You’ll work on our **agentic learning environment**: the loops that turn human corrections and agent outcomes into better knowledge and instructions over time. This role combines **applied research** with **ownership of production systems**. You’ll identify failures, form hypotheses, run experiments, and ship fixes into real customer workflows. ## What You’ll Do - Build and extend our **core context-learning library**, turning customer-informed problems into reusable platform capabilities. - Design and implement **LLM-powered systems** and **agentic workflows** from concept to production. - Build agentic features for **knowledge management** (agents that can edit, update, and maintain large knowledge bases autonomously). - Create **continuous learning loops** using human corrections and production outcomes to find knowledge gaps, detect changed procedures, and improve prompts/instructions. - Build **reliability and confidence systems**: evaluation frameworks, confidence scoring, and logic for when to automate vs. escalate to a human. - Architect **async, scalable systems** for complex AI orchestration. - Contribute to the direction of our **AI strategy** and product capabilities. ## What We’re Looking For - Experience building **complex, production LLM systems**, with depth in the engineering decisions you can explain (including what changed after real users arrived). - Practical depth in one or more of: **context engineering, retrieval, agent orchestration, memory, evaluation, learning from feedback**. - Strong experimental judgment: turn ambiguous problems into testable hypotheses, set baselines, and distinguish real improvements from noise. - Excitement for open-ended problems where the solution may not exist yet. - Comfort moving between **research papers and production code**. - Strong communication skills with teammates and customers. - **3+ years** of professional experience. Don’t meet every trait? We still encourage you to apply. ## Learn More About Edra - Series A announcement video: https://www.linkedin.com/posts/eugen-alpeza_at-palantir-yannis-and-i-spent-years-doing-activity-7440038397383032832-Di8f?utm_source=share&utm_medium=member_desktop&rcm=ACoAABJB3z0BkalWJ3s4sVxB7Gz6TE_b-i8IMto - Launch blog post: https://www.linkedin.com/pulse/edra-out-stealth-edra-ai-wecqe/ - What we’re building: https://x.com/edra_ai/status/2034268633308742073 - Founders’ point of view: https://x.com/EugenAlpeza/status/2104936003282546913?s=20 ## Compensation & Benefits - Co
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.