AI Systems Engineer - Agentic Autonomy

Bachelor’s, Master’s, or PhD in Computer Science, Machine Learning, Robotics, or a related field. Deep hands-on experience building with LLMs and multi-agent/agentic AI frameworks. Strong software engineering background in modern ML frameworks, cloud orchestration, and API development. Experience integrating AI systems into larger software architectures or robotics/autonomy workflows. Understanding of RAG pipelines, tool-use frameworks, LLM function-calling, memory systems, and agent orchestration. Experience with safety evaluation, model alignment, or mission-critical AI system validation. Ability to lead system-level design discussions and coordinate across multiple engineering disciplines. Must be a U.S. Citizen and eligible to obtain a Secret Clearance.

Lead the design and development of LLM-powered software modules for mission reasoning, planning, operator interaction, and autonomous decision support. Integrate LLMs and agentic systems into HavocAI’s autonomy architecture, including ROS/ROS2 systems, planning engines, and mission software. Build multi-agent, tool-using AI systems that interact with perception data, mission databases, simulation systems, and operator inputs. Develop APIs, wrappers, and orchestration layers enabling LLMs to interface safely with embedded, cloud, and edge compute environments. Optimize LLM inference pipelines for performance, latency, and reliability in field-deployed systems. Evaluate model behavior, perform safety testing, and develop guardrails for mission-critical use cases. Collaborate with autonomy, embedded, simulation, and full-stack teams to define requirements and ensure robust system-level integration. Guide strategic decisions on model selection, fine-tuning approaches, safety frameworks, and long-term AI architecture. Contribute to field testing, operator evaluations, and iterative deployment cycles for AI-augmented autonomy systems.