
Applied Super Intelligence Engineer, Physical Systems
Lawrence Livermore National Laboratory1 day ago
Base Salary
$122k - $186k/yr
Responsibilities
- Implement agent-facing tool definitions and task workflows using documented equipment interfaces and platform services.
- Develop multimodal perception and decision-support workflows using camera, telemetry, process, sensor, and operational data.
- Improve prompt logic, tool use, evaluation methods, guardrails, failure analysis, and workflow reliability.
- Translate operational tasks into safe, testable, maintainable SI-assisted workflows with defined approval points and fallback behaviors.
- Evaluate and debug workflows through logging, iterative refinement, and disciplined software engineering practices.
- At the higher level, design multicomponent agent workflows, improve reusable evaluation harnesses, coordinate with embedded and platform engineers, and provide informal guidance to less-experienced contributors.
Requirements
- Ability to secure and maintain a U.S. Department of Energy Q-level security clearance; U.S. citizenship is required.
- Bachelor’s degree in computer science, software engineering, robotics, or a related field, or an equivalent combination of education and related experience.
- Proficiency in Python or a comparable programming language for applications, prototypes, or internal tools.
- Experience from coursework, projects, research, internships, or professional work developing LLM, multimodal, agent-based, or tool-calling applications.
- Experience designing, implementing, testing, and debugging tool-using SI workflows connecting models to APIs, services, data sources, or operational systems, including structured contracts, error handling, logging, and evaluation.
- Experience working with real-world data from sensors, cameras, devices, or operational systems.
- Familiarity with version control, automated testing, and collaborative code review.
- At the higher level, ability to independently develop and evaluate multicomponent workflows and debug moderately complex failures involving perception, tool use, integration, and operational constraints.
- Preferred qualifications include exposure to robotics workflows, ROS or ROS 2; vision-language or vision-language-action models; multimodal perception pipelines; simulation, digital twins, or hardware-in-the-loop testing; workflow orchestration; agent tracing or evaluation systems; prompt or configuration versioning; replay-based testing; and MQTT or NATS.
Benefits
- Hybrid schedule with the flexibility to work from home one or more days per week.
- Flexible Benefits Package.
- 401(k).
- Relocation assistance.
- Education reimbursement program.
- Flexible schedules depending on project needs.
- Career Indefinite position open to LLNL employees and external candidates.
- Requires a post-offer, pre-employment drug test and may involve restrictions on personal wireless or medical devices in DOE Limited Areas.
Tech Stack
Categories
About Lawrence Livermore National Laboratory
Lawrence Livermore National Laboratory (LLNL) is a U.S. Department of Energy/National Nuclear Security Administration laboratory in Livermore, California, conducting research for national security, energy, and fundamental science. Founded in 1952 and operated by Lawrence Livermore National Security, LLC, LLNL’s portfolio spans stockpile stewardship, high-performance computing, and the National Ignition Facility laser program, with work funded primarily through federal contracts and appropriations for defense, intelligence, and civilian agencies.