Backend Infrastructure & Agentic AI Software Engineer

Backend Infrastructure & Agentic AI Software Engineer The Opportunity: The G RACE team at ARPA-H is building the next generation of agentic AI to transform how the agency accelerates research, makes decisions, and ships products at scale. G RACE is ARPA-H's production AI assistant, and we are evolving it into an ecosystem of autonomous, multi-agent systems.

We are a small, startup-minded team that ships fast and owns what we build end-to-end. We are looking for a senior software development engineer who can own the backend infrastructure G RACE runs on, while also being a first-principles builder of the agentic AI systems that run on top of it.

On a lean team, infra and AI are not separate concerns. You will own both, and you will treat production reliability, token economics, security, and observability as non-negotiable from day one. The best person for this role starts with the user.

They ask why before they ask how. They communicate clearly, give and receive feedback well, and make the people around them better. They have a high bar, a high sense of urgency, and they play well with others. What You’ll Work On: Own the end-to-end backend infrastructure for G RACE on Micro sof t Azure, including Azure Functions, Azure API Management, Azure Container Apps, and Azure OpenAI Service.

Own the data layer, including storage, retrieval pipelines, and vector databases, and document indexing that power G RACE 's internal knowledge search. Own authentication and identity integration, including ARPA-H Entra ID and application-level access control.

Implement and maintain infrastructure as code for all environments. Own CI / CD pipelines, deployment automation, and release processes, including canary and gradual rollouts. Own the basics that are non-negotiable on any production system, including monitoring, alerting, logging, distributed tracing, SLOs, and incident response runbooks.

Manage secrets, API keys, and credential rotation across all integrations with external providers. Own cost and token economics across all LLM providers and track spend, set budget s, build guardrails, and optimize for cost-per-query without sacrificing quality.

Own the backend implementation of MCP, including MCP server hosting, tool registration, versioning, and lifecycle management on Azure. Implement and evolve A2A communication patterns, enabling G RACE agents to interoperate with each other and with external agent systems.

Design and maintain LLM orchestration, routing, and multi-model switching infrastructure across OpenAI GPT, Anthropic Claude, and Google Gemini families. Build and operate RAG pipelines, including document ingestion, chunking, embedding, and semantic search.

Implement robust fallback, retry, circuit-breaker, and g race ful degradation patterns for all AI service dependencies. Own tool-calling infrastructure, including registration, execution, error handling, and observability for all G RACE tools.

Build and maintain end-to-end observability for agentic workflows, including latency, throughput, error rates, token usage, and LLM quality met rics. Implement LLM evaluation pipelines, including safety checks, regression monitoring, and grounding assessment.

Define and enforce system-level SLOs for availability, response time, and tool call reliability. Own alerting and on-call runbooks and be the person who knows what broke and why. Establish and improve coding standards and design review processes and testing practices.

Communicate technical decisions clearly, in writing and in conversation, to both engineers and non-engineers. Mentor and unblock other engineers with a bias toward ownership and speed. Work backward from the user and understand the problem being solved before proposing a solution.

Ensure strong privacy, security, and compliance in all systems, integrations, and data handling. Join us. The world can’t wait. You Have: 7+ years of experience in sof tware engineering, building and operating production systems 5+ years of experience in high-velocity environments where you owned and shipped complex products end-to-end 5+ years of experience in Python and at least one other backend language, including modern backend frameworks and async patterns 5+ years of experience with distributed systems, APIs, data pipelines, and sof tware design patterns 5+ years of experience with Micro sof t Azure, including Azure Functions, API Management, Container Apps, and Azure OpenAI Service 5+ years of experience with containerization, CI / CD, and infrastructure as code 5+ years of experience owning production systems, including being on-call, debugging incidents, and writing the postmortem Knowledge of authentication and identity systems such as OAuth2, OIDC, pr Azure Entra ID Ability to give and receive feedback well Bachelor's degree in Computer Science or Sof tware Engineering Nice If You Have: 5+ years of experience building and operating MCP servers in production, including tool registration, versioning, and hosting on Azure Functions or equivalent serverless infrastructure 5+ years of experience implementing A2A communication patterns and multi-agent orchestration frameworks 5+ years of experience building on top of LLMs in production, including tool-calling, RAG, multi-step reasoning, multi-model routing, and context window management 5+ years of experience in token economics, including cost-per-query, context budget s, and prompt efficiency as first-class engineering concerns 5+ years of experience managing multi-provider LLM integrations, including rate limits, fallback routing, and API versioning 5+ years of experience in security-conscious engineering in regulated or government environments 5+ years of experience in startup or early-stage environments, including 0-to-1 product building, comfort with ambiguity, and high sense of urgency 5+ years of experience in big tech building customer-facing platforms or developer infrastructure at scale Experience with vector databases, embedding pipelines, and semantic search infrastructure Master’s degree in Computer Science, Sof tware Engineering, or a related field Compensation At Booz Allen, we celebrate your contributions, provide you with opportunities and choices, and support your total well-being.

Our offerings include health, life, disability, financial, and retirement benefits, as well as paid leave, professional development, tuition assistance, work-life programs, and dependent care. Our recognition awards program acknowledges employees for exceptional performance and superior demonstration of our values.

Full-time and part-time employees working at least 20 hours a week on a regular basis are eligible to participate in Booz Allen’s benefit programs. Individuals that do not meet the threshold are only eligible for select offerings, not inclusive of health benefits.

We encourage you to learn more about our total benefits by visiting the Resource page on our Careers site and reviewing Our Employee Benefits page. Salary at Booz Allen is determined by various factors, including but not limited to location, the individual’s particular combination of education, knowledge, skills, competencies, and experience, as well as contract-specific affordability and organizational requirements.

The projected compensation range for this position is $99,000.00 to $225,000.00 (annualized USD). The estimate displayed represents the typical salary range for this position and is just one component of Booz Allen’s total compensation package for employees.

This posting will close within 90 days from the Posting Date. Identity Statement As part of the hiring process, we will ask you to complete an identity verification process that leverages advanced biometrics and artificial intelligence to ensure authenticity and protect against identity fraud.

You are expected to be on camera during interviews and assessments. We reserve the right to take your picture to verify your identity and prevent fraud. Candidate AI Usage Policy AI is a part of our daily work at Booz Allen, and we are committed to the responsible and ethical use of AI tools.

However, we want to ensure a fair candidate process based on your own skills and knowledge. As part of this commitment, the use of artificial intelligence (AI) or other tools to assist with responses during interviews (whether in-person or virtual) is prohibited unless permission is explicitly provided .

Work Model Our people-first culture prioritizes the benefits of collaboration, whether it occurs in person or virtually. To support engagement and effective communication, employees working virtually are generally expected to have their cameras on during meetings.

Remote : If this position is listed as remote, there may still be occasions when you are required to work in person at a Booz Allen or customer facility. Hybrid : If this position is listed as hybrid, you will be expected to work from a Booz Allen facility frequently, in alignment with leadership expectations and the needs of the role.

You may also be required to work from or visit a customer facility. Onsite : If this position is listed as onsite, work will primarily be performed at a Booz Allen office or customer facility, where employees will collaborate directly with colleagues and customers as required by the role.

Commitment to Non-Discrimination All qualified applicants will receive consideration for employment without regard to disability, status as a protected veteran or any other status protected by applicable federal, state, local, or international law.