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.

• Own the end‑to‑end backend infrastructure for G RACE on Microsoft 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  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 budgets, 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 graceful 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 metrics.
• 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.

• 7+ years of experience in software 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…