About the role
Aslan builds AI for the people who protect this country. The work matters. The stakes are not abstract.
You’ll build the core reasoning and orchestration layer behind Aslan’s platform — multi-agent systems, supervisory logic, long-horizon autonomous planning, tool use, and real-world grounding — in adversarial, non-deterministic environments where reliability isn’t optional and the downstream consequences of getting it wrong are not measured in churn.
If your instinct when facing a new problem is to reach for a framework, this isn’t the role. If your instinct is to read the paper, understand the mechanism, and build the minimal thing that actually works — keep reading.
What You’ll Do
- Design and implement multi-agent architectures: supervisory agents, planning layers, session management, tool orchestration, and failure recovery across long-running autonomous workflows
- Build and refine the reasoning and decision-making systems that govern complex autonomous behavior — strategic adaptivity, environmental awareness, and adversarial resilience
- Develop evaluation and observability infrastructure for agentic systems operating in real-world, non-deterministic environments
- Architect LLM integration patterns (structured generation, function calling, context management) with a deep understanding of model behavior, failure modes, and capability boundaries
- Prototype aggressively — the correct answer to “can we do X” is a working proof-of concept by end of day, not a design doc by end of week
- Work across the stack as needed — Python, TypeScript, infrastructure — with primary ownership of the AI/reasoning layer
- Collaborate directly with the founder and field engineers to translate mission requirements into agent capabilities on compressed timescales