Forward Deployed AI Engineer (New York)

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 run 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, and we're growing our team in New York and London. We're a deeply technical team of engineers, AI researchers, and strategists with a high bar for talent and a shared belief that exceptional people are the foundation of everything great we'll build. The Role We're building a learning system that teaches AI agents how enterprises actually work. Our system ingests knowledge bases, conversations, tickets, and system logs, then produces written instructions that agents can execute–with confidence scoring to know when to automate and when to seek human input. We're looking for Forward Deployed AI Engineers who have built complex, production LLM-based systems, and want to work directly with our enterprise customers. Whether you've scaled LLM workflows handling millions of requests, built multi-agent systems in production, or designed evaluation frameworks for enterprise deployments, we want people who bring intensity and self-direction to their craft. You’ll own the full technical journey: understanding how a [... source excerpt omitted ...] dentifying the right problem, designing and building the solution, shipping it to production, driving adoption, and expanding its impact. This is an engineering role: you’ll write production code, make architectural decisions, build agentic systems, and take responsibility for the outcome. What You'll Do Work directly with enterprise customers to identify new problems, prototype solutions, and ship them to production Own customer engagements from discovery and solution design through production, adoption, and expansion. Design and implement LLM-powered systems and agentic workflows from concept to production Use and extend our core context-learning library to solve customer pr [... source excerpt omitted ...] d logic for when to automate vs. when to escalate to a human Architect async, scalable systems that handle complex AI orchestration What We’re Looking For You've built complex, production LLM-based systems with real depth–something with multiple layers of engineering decisions you can walk through in detail You've shipped something meaningful to production and can explain how it evolved You're excited by open-ended problems where the solution might not exist yet You have experience with (or strong interest in) how systems learn and improve over time: human-in-the-loop feedback, prompt optimization and context engineering You have experience building agents and autonomous sys