What You’ll Do
– Design and deploy scalable, fault-tolerant AI systems for cyber operations.
– Build orchestration frameworks that coordinate multiple AI models and tools.
– Develop robust model control plane (MCP) server infrastructure.
– Create advanced prompt engineering strategies tailored to complex operational scenarios.
– Build resilient API layers that handle model failures and edge cases gracefully.
– Rapidly prototype new capabilities while maintaining production-quality standards.
– Mentor junior engineers and contribute to a high-performance engineering culture.
– Lead architectural decisions that balance innovation with operational reliability.
– Drive technical discussions on AI capabilities, limitations, and strategic use cases.
– Deliver proof-of-concepts that demonstrate breakthrough capabilities. What You Bring
– 12+ years of software engineering experience, with deep expertise in Python.
– Proven experience deploying AI-powered applications in production environments.
– Strong knowledge of modern AI architectures (agents, RAG, chains, function calling).
– Hands-on experience integrating multiple AI services and managing failure modes.
– Experience with MCP servers or similar model-serving infrastructure.
– Advanced prompt engineering skills with real-world results.
– Expertise in building distributed systems and managing asynchronous workflows.
– Deep understanding of AI model behavior, limitations, and provider ecosystems.
– Excellent debugging skills, especially for non-deterministic AI behavior.
– A track record of solving novel technical problems without existing playbooks.
Location: Maryland, Columbia
Apply Now