> Markdown version of [/jobs/ext/3608708-senior-ai-platform-engineer](https://www.wearedevelopers.com/jobs/ext/3608708-senior-ai-platform-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Senior AI Platform Engineer

- **Company:** Eleven, Inc.
- **Location:** New York, NY, United States
- **Experience:** Expert
- **Salary:** $228,800.0 - $270,400.0
- **Contract:** Permanent contract
- **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Cloud Engineering, Software Engineering, Workflow Management Systems, Enterprise Software Applications, Large Language Models, Agentic-AI, Build Management, AI Platforms, Low Latency, Invoking Functions
- **Published:** October 7, 2026
- **Apply:** https://www.disabledperson.com/jobs/75816498-senior-ai-platform-engineer

## About the Role

* Strong software engineering and distributed-systems fundamentals, with experience building production platform services.
 * Hands-on experience building production applications with LLMs, agents, tool/function calling or workflow orchestration.
 * Experience with asynchronous execution, state management, queues/workflows, retries, observability and failure recovery.
 * Understanding of model APIs, routing, structured outputs, context management and AI quality/cost tradeoffs.
 * Cloud-native engineering experience with containers, APIs and secure production systems

## Description

* Design and build agent runtime services for long-running, asynchronous and stateful AI workloads.
 * Build model abstraction and routing capabilities that optimize quality, latency, reliability and cost across multiple AI providers and models.
 * Implement tool invocation, execution state, retries, checkpoints, failure recovery and control mechanisms for production agents.
 * Develop APIs and SDKs that let teams compose agentic workflows and reusable AI capabilities on top of AIVA.
 * Build tracing, telemetry and evaluation into the runtime so agent behavior and outcomes can be measured and governed.
 * Partner with security, identity, integration and platform engineers to safely expose enterprise systems and execution environments to agents.