Note: The job is a remote job and is open to candidates in USA. Elios AI is a fast-growing financial advisory and accounting firm building an in-house AI platform team. They are seeking an AI Platform Engineer to design and maintain the agent runtime for Claude agents in production, while also owning the LLM abstraction layer and defining reusable patterns for other engineers.

Responsibilities

• Design and maintain the agent runtime that orchestrates Claude agents in production: session lifecycle, SSE event streaming with reconnect and de-duplication, and crash-safe tool dispatch
• Own the LLM abstraction layer, including a provider-agnostic client, a versioned prompt registry with templating, and the migration path from Azure AI Foundry to native Anthropic endpoints
• Define the patterns other engineers extend, like the behaviour-plus-mock interface for external services and tool definitions as composable actions
• Operate the deployment and integration plumbing: background-job orchestration, multi-environment rollout, secret management, and connectors to enterprise systems
• Harvest a team's proven workflow into a versioned, shareable Skill or platform capability
• Partner with Forward Deployed Engineers and product squads to productize what works in one workflow into a capability every team can adopt

Skills

• 5+ years in systems engineering, with strong experience in a functional and/or concurrent language. Elixir/OTP is a plus, but deep functional or distributed-systems experience plus willingness to ramp is what matters
• Hands-on experience building LLM or agent applications: tool and function calling, structured output, prompt design, and streaming
• Fluency with distributed and streaming systems: supervision, backpressure, retries, idempotency, and graceful degradation
• Cloud infrastructure and deployment experience (Azure or AWS), plus real testing discipline with dependency injection and mocks at service boundaries
• Comfort working across an Elixir and Python boundary
• Direct experience with the Anthropic API: Claude tool use, the Managed Agents API, MCP, or Skills
• Familiarity with actor and agent frameworks, SQL analytics, or observability tooling
• Background in finance, accounting, audit, or another compliance-sensitive domain

Company Overview