AI Research Engineer

About Dropzone AI

Dropzone’s mission is to scale cybersecurity beyond human limits, and augment every single human security engineer/analyst with an army of AI security specialists. Humans alone cannot sufficiently protect our digital future, and AI augmentation is the only way for defenders to reclaim the high ground. We are an award winning company disrupting the $200B+ cybersecurity market. 

Powered by Gen AI advancements, our technology offloads repetitive day-to-day work and frees human analysts to focus on real threats and higher-value projects. We are venture-backed, and our team has a rare blend of deep experience across cybersecurity, AI/ML, and SaaS product development. Join us if you want to be on the ground floor of using Gen AI to transform cyber defense. Learn more at www.dropzone.ai .

About the role

We are seeking a Senior to Principal-level AI Research Engineer to lead the design and development of next-generation agentic AI systems. This role sits at the intersection of research and production, with a strong emphasis on:

Agent architecture design

Harness and memory engineering

Robust evaluation and benchmarking of model and agent performance

You will work closely with product and engineering teams to translate cutting-edge research into scalable, real-world systems. 

In this role, you will directly shape the core intelligence layer of Dropzone AI. Your work will define how our agents reason, remember, and improve over time, influencing both our product capabilities and the broader direction of applied AI systems.

What we're looking for

Someone who thinks in context/harness engineering, not just models

A learner who can follow latest research and test them in real-world deployment

Deep curiosity about how to convert non deterministic outputs from LLMs to consistent reliable outcomes and replicate expert human intuitions 

Strong ownership mindset and ability to drive ambiguous problems to clarity

What you'll do

Agentic Architecture

Design and implement advanced multi-step reasoning agents (tool use, planning, reflection, self-improvement loops)

Develop frameworks for multi-agent coordination and task decomposition

Improve reliability, latency, and cost efficiency of agent execution

Memory Systems

Architect short-term and long-term memory subsystems (episodic, semantic, retrieval-based, hybrid)

Build mechanisms for context compression, retrieval, and grounding

Explore novel approaches to continual learning and state persistence

Evaluation & Reliability

Define 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 production

Research → Production

Translate latest community research ideas into production-grade systems

Run experiments, analyze results, and iterate quickly

Contribute to internal knowledge sharing and technical direction

Requirements

5+ years in software engineering, with at least 1+ year applying GenAI in production

Proven experience building or researching:

Agent frameworks / tool-using LLMs

Memory / retrieval systems (RAG, vector DBs, hybrid retrieval)

Expert Python developer

Familiar with openclaw and Claude Code harness architecture

Early-stage startup mindset. You thrive on ambiguity and move with lightspeed execution

Preferred

Experience with agent orchestration frameworks (LangGraph, AutoGen, custom systems)

Familiarity with AI safety guardrails, hallucination mitigation, and structured output enforcement

Experience designing LLM evals (offline + online, human-in-the-loop, synthetic data)

Publications or open-source contributions in relevant areas

Experience applying latest context/harness engineering techniques to customer facing products

Founder or early-stage (first 10 engineers) or experience in st …