airmy.dev/company/research
/ AIRMY Research
Pushing the frontier
of production AI.
AIRMY Research publishes work on inference optimisation, agent safety, multi-agent systems, and the infrastructure challenges of deploying AI at scale.
4
Research Areas
0
Published Papers (yet)
Early
Stage program
/ Research Areas
Where we focus.
Our research is grounded in the hard problems we encounter running AI infrastructure at production scale.
Inference Optimisation
Speculative decoding, KV-cache management, and batching strategies for sub-50ms P99 latency at scale.
Agent Safety & Alignment
Formalising safety constraints for autonomous agents, detection of goal misgeneralisation, and sandboxed execution environments.
Multi-Agent Orchestration
Coordination protocols for heterogeneous agent networks, task decomposition, and emergent behaviour in large agent graphs.
Context & Memory
Efficient long-context architectures, persistent memory systems, and retrieval-augmented generation for production agents.
Human-Agent Collaboration
Studying optimal handoff patterns, oversight mechanisms, and trust calibration between human operators and autonomous systems.
Evaluation & Benchmarking
Reproducible evaluation frameworks, domain-specific benchmarks, and capability elicitation methodologies.
/ Publications
Research direction, publications coming.
We are focused on production agent infrastructure — safety, orchestration, and observability at scale. Formal publications are not published yet.
In the meantime, read engineering notes and product updates on the AIRMY blog.
Visit the blog/ Research Team
Growing the program.
AIRMY research is early-stage and tied to product engineering. We are not hiring a separate research lab yet — but we are interested in people who want to work on production agent systems.
View open roles