Entry-Level AI Agent Systems Engineer

Koitecc Solutions; Albuquerque (NM); On-site; USD 102,000 - 200,000; Full time

Benefits offered by this job

Onsite work

Relocation assistance

Generous vacation

Job summary

Sandia National Laboratories seeks researchers to design and optimize agent and multi-agent AI tooling in a national security context. You will define development lifecycles, collaborate with researchers from multiple disciplines, and build robust evaluation pipelines to ensure safety, reliability, and performance across scales.

The role requires strong software engineering, experience with AI/ML, and the ability to deploy and scale AI capabilities onsite with potential relocation.

Qualifications

• Bachelor's degree or equivalent in a relevant field.
• Ability to obtain and maintain a DOE Q and SCI clearance.
• Experience with AI, ML, and agent/multi-agent systems.
• Strong software engineering fundamentals.

Responsibilities

• Design, develop, and optimize agent and multi-agent AI tooling and workflows against technical goals, domain context and operating environment, and success metrics.
• Define and apply an agentic system's development lifecycle, including requirements, analysis, architecture design, model and agent selection, tool integration, testing, deployment, and continuous improvement.
• Work with researchers in other sciences to develop evaluation frameworks to measure and communicate system reliability, trustworthiness, safety, accuracy, and national security impact.
• Build automated evaluation and regression-testing pipelines for prompts, tools, models, workflows, and emergent agent behaviors.
• Integrate agent capabilities with tools, APIs, orchestration frameworks, and agent architectures.
• Establish and operate LLMOps/AgentOps practices including CI/CD, automated testing, monitoring, telemetry, cost tracking, and incident response for AI agents in production.
• Deploy and scale agent AI capabilities across the laboratory and customer implementations.
• Continuously evaluate new models, frameworks, architectures, and methodologies, and translate relevant advances to improve system quality and performance.
• Work with human systems integration teams to ensure efficacy of overall agentic system; assess human-agent team performance, including whether users can effectively understand, supervise, collaborate with, and accomplish their work through the system.

Skills

AI tooling

Agent systems

Python

APIs

Education

Bachelor's degree

Tools

LangChain

Kubernetes

API design

Job description

Sandia National Laboratories seeks researchers to design and optimize agent and multi-agent AI tooling in a national security context. You will define development lifecycles, collaborate with researchers from multiple disciplines, and build robust evaluation pipelines to ensure safety, reliability, and performance across scales.

The role requires strong software engineering, experience with AI/ML, and the ability to deploy and scale AI capabilities onsite with potential relocation.