[Remote] AI Research Engineer

Note: The job is a remote job and is open to candidates in USA. Dropzone AI is on a mission to scale cybersecurity through AI augmentation, aiming to enhance the capabilities of human security engineers. They are seeking a Senior to Principal-level AI Research Engineer to lead the design and development of advanced AI systems, focusing on agent architecture, memory engineering, and model evaluation. This role involves translating cutting-edge research into practical applications that improve cyber defense.ResponsibilitiesDesign and implement advanced multi-step reasoning agents (tool use, planning, reflection, self-improvement loops)Develop frameworks for multi-agent coordination and task decompositionImprove reliability, latency, and cost efficiency of agent executionArchitect short-term and long-term memory subsystems (episodic, semantic, retrieval-based, hybrid)Build mechanisms for context compression, retrieval, and groundingExplore novel approaches to continual learning and state persistenceDefine and implement evaluation frameworks for agent performance (task success, reasoning quality, robustness)Build automated eval pipelines (synthetic data, adversarial testing, regression testing)Establish metrics and benchmarks for agent reliability in productionTranslate latest community research ideas into production-grade systemsRun experiments, analyze results, and iterate quicklyContribute to internal knowledge sharing and technical directionSkills5+ years in software engineering, with at least 1+ year applying GenAI in productionProven experience building or researching: Agent frameworks / tool-using LLMsProven experience building or researching: Memory / retrieval systems (RAG, vector DBs, hybrid retrieval)Expert Python developerFamiliar with openclaw and Claude Code harness architectureEarly-stage startup mindset. You thrive on ambiguity and move with lightspeed executionExperience with agent orchestration frameworks (LangGraph, AutoGen, custom systems)Familiarity with AI safety guardrails, hallucination mitigation, and structured output enforcementExperience designing LLM evals (offline + online, human-in-the-loop, synthetic data)Publications or open-source contributions in relevant areasExperience applying latest context/harness engineering techniques to customer facing productsFounder or early-stage (first 10 engineers) or experience in standing up a new technology bet within a more established companyBenefitsCompany paid health insurance401K Plan with employer matchSelf-Managed PTOParental leaveCompany-provided equipmentCompany OverviewDropzone AI delivers pre-trained autonomous AI security agents that work alongside human analysts on security operations teams It was founded in 2023, and is headquartered in Seattle, Washington, USA, with a workforce of 51-200 employees. Its website is https://dropzone.ai.Company H1B SponsorshipDropzone AI has a track record of offering H1B sponsorships, with 1 in 2023. Please note that this does not guarantee sponsorship for this specific role.