AI Software Engineer

AI Software Engineer

The Opportunity: 

To achieve an organization’s mission, leaders need strong team members who can create and analyze processes, communicate requirements, and develop innovative solutions throughout the execution of the mission. Whether reviewing program-wide technical architecture or providing AI expertise, our clients need someone who combines deep technical understanding of software engineering with strong architectural judgment. That is why we need you, an experienced AI Software Engineer who can operate at a system-of-systems level to support clients in advancing AI-enabled systems within an R&D environment.

As part of our team, you'll serve as Software Development Engineer to the Advanced Research Projects Agency for Health (ARPA-H), helping conceptualize, create, and execute advanced government-funded research and development programs to accelerate better health outcomes for everyone. Work with world-class scientists and engineers to support the development of high-impact solutions to society's most challenging health problems. Leverage technical expertise to provide strategic assessments of new technologies in support to senior ARPA-H decision makers. Maintain responsibility for producing and presenting findings and recommendations to a team of colleagues and clients on the feasibility and potential impact of future research programs, assisting with the management of current programs, and facilitating commercialization of successfully developed technologies. 

You'll serve as an AI Software Engineer advising program leadership and supporting software engineering to support the client mission. You will support clients in ensuring that program-wide technical architecture and engineering to rigorous AI development, evaluation, and long-term impact. Your attention to detail, flexibility, communication skills, understanding of the client's mission, and problem-solving will enable the mission's success.

What You’ll Work On

• Develop and implement core agentic systems and workflows by implementing tool-calling, multi-step reasoning, memory, and agent-to-agent (A2A) communication patterns.

• Develop and implement LLM evaluation pipelines, and build and maintain Model Context Protocol (MCP) integrations.

• Build LLM-powered features including prompt orchestration, RAG pipelines, grounding and evaluation systems, and context management across model families, such as OpenAI, Anthropic, or Google.

• Design and implement backend features end-to-end, including APIs, integrations with data sources, such as Dimensions, Slack, or SharePoint, and robust error handling.

• Implement and iterate on prompt engineering patterns and system prompts that drive quality and consistency across model families. Build LLM evaluation components such as grounding assessment, regression tests, safety check, and quality metrics.

• Write prompts and pipelines with considerations to token economics.

• Contribute to infrastructure and DevOps, working with Microsoft Azure, such as Functions, API Management, or Container Apps, and maintaining CI/CD, monitoring, and observability systems.

• Collaborate cross-functionally with engineers, PMs, and researchers to deliver clear, user-focused solutions and communicate technical decisions effectively.

• Ensure production reliability and privacy, meeting service-level objectives while maintaining security, compliance, and graceful degradation under failures.

Join us. The world can’t wait.

You Have:  

• 3+ years of experience building and operating production-grade software systems

• Experience with algorithms, data structures, distributed systems, design patterns, cloud platforms, such as Azure, AWS, or GCP, and containerization, such as Docker

• Experience working with CI/CD pipelines and working in high-velocity, end-to-end delivery environments

• Experience interacting and communicating with senior-level executives, including SES or GS-15 

• Experience with using Microsoft Office, Excel, Word, and PowerPoint

• Knowledge of modern backend frameworks and asynchronous programming models

• Ability to work in at least 2 backend programming languages, including Python and async patterns

• Ability to operate independently within a fast-paced start-up environment involving CI/CD pipelines and produce clear, actionable product stories and specs

• Ability to obtain and maintain a Public Trust or Suitability/Fitness determination based on client requirements

• Bachelor’s in Computer Science or Software Engineering

Nice If You Have:  

• Experience with LLM integration, such as tool-callin