Jobs at Scale AI

As a Mission Software Engineer, you'll develop solutions for government customers by integrating software into existing workflows, requiring significant travel, collaboration, and technical expertise.

Lead the architecture and production deployment of agentic AI systems for classified and mission-critical government environments. Build systems for geospatial reasoning, retrieval, embeddings, persistent memory, orchestration, evaluation, and reliability. Own shared ML infrastructure, define technical direction, partner across engineering and research teams, mentor engineers, and drive ambiguous initiatives from prototype to supported production capability.

Owns the architecture, development, evaluation, and production deployment of generative AI, agentic AI, computer vision, and reinforcement learning systems for mission-critical government applications. Responsibilities include building scalable ML infrastructure, improving models through tuning and retraining, developing evaluation benchmarks, partnering with users and research teams, mentoring engineers, and designing for classified and resource-constrained environments.

Deploy and maintain state-of-the-art ML models (LLMs and vision) in production for government customers. Improve models via retraining, tuning, and architecture updates; build scalable ML infrastructure; prototype ML-driven product enhancements; work with massive datasets and multimodal fine-tuning pipelines; collaborate across research, product, and engineering. Requires active security clearance and light travel (~10%).

Embed with U.S. government customers to design, build, deploy, and maintain mission software from prototype to production. Own end-to-end delivery, build backend systems and data integrations, collaborate with product and engineering to scale reusable capabilities, and serve as the technical point of contact to drive adoption and mission impact.

Conduct empirical AI safety research with mentor guidance, owning projects from hypotheses and controlled experiments through analysis and technical writing. Build and debug evaluation harnesses, agent environments, datasets, monitoring methods, and post-training experiments. Investigate model failures, alignment, deception, misuse, multi-agent risks, and evaluation reliability. Produce reproducible code, experiment logs, research analyses, and papers for potential submission to leading machine learning conferences.

Paid, part-time Creative Advisor collaborating with AI research and machine learning teams. The role involves sharing creative expertise, defining quality standards, developing work, reviewing model outputs, identifying limitations, and helping fellow creators engage with the program. Applicants should be leading creators with strong portfolios and interest in shaping AI’s impact on creative practice; no AI experience is required.

Perform part-time quality audits and evaluations of task outputs, define and refine quality benchmarks and scoring rubrics, analyze audit results to produce actionable insights and reports, and recommend process improvements to raise output quality.