AI Research Engineer (New York)
About The Position
Edra is seeking AI Research Engineers to build a learning system that teaches AI agents how enterprises operate. The system analyzes customer evidence such as knowledge base articles, support conversations, tickets, system logs, and agent traces to reverse-engineer business processes and document them as instructions that people can inspect and agents can execute. Confidence scoring helps determine when to automate and when to seek human input. The role combines applied research with ownership of production systems. Engineers will work on the agentic learning environment, including loops that use human corrections and agent outcomes to improve knowledge and instructions over time. The work focuses on advancing Edra’s core context-learning library and the harness that powers agents across customers, spanning continuous learning, context engineering, agent orchestration, and evaluation. The position also contributes to knowledge benchmarks and the harness’s self-improving capabilities.
Requirements
- At least 3 years of professional experience.
- Experience building a complex, production LLM system, with the ability to explain engineering decisions and how the system changed after real users arrived.
- Practical depth in one or more of context engineering, retrieval, agent orchestration, memory, evaluation, or learning from feedback.
- Experimental judgment: ability to turn ambiguous problems into testable hypotheses, set baselines, and distinguish real improvements from noise.
- Comfort navigating both research papers and production code.
- Strong communication skills and ability to explain work to teammates and customers.
- Self-direction and interest in open-ended problems where the solution may not yet exist.
Responsibilities
- Build and extend the core context-learning library, turning customer-informed problems into reusable platform capabilities.
- Design and implement LLM-powered systems and agentic workflows from concept through production.
- Build agentic knowledge-management features that autonomously edit, update, and maintain large knowledge bases.
- Build continuous-learning loops that use human corrections and production outcomes to find knowledge gaps, detect changed procedures, and improve prompts and instructions.
- Build reliability and confidence systems, including evaluation frameworks, confidence scoring, and logic for when to automate or escalate to a human.
- Architect asynchronous, scalable systems for complex AI orchestration.
- Contribute to the direction of Edra’s AI strategy and product capabilities.
Benefits
- Competitive base salary and meaningful equity.
- Top-tier health, dental, and vision plans, with 100% premium coverage in the US and a One Medical membership.
- Private medical and dental coverage in the UK.
- Flexible paid time off.
- Lunch provided in the office most days, plus snacks and drinks.
- A stipend to set up a workspace.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
Education Level
No Education Listed
