About Thira
Thira is the CIO's trusted agentic AI platform that continuously learns and executes repetitive IT work. Enterprises will spend $6.3 trillion on IT this year, and roughly 40% of it goes to people doing repetitive work across systems that were never built to work together. The work arrives faster than any team can absorb it, the backlog never clears, and there's no capacity left for the work that moves the business forward. Thira learns how an enterprise actually runs, finds a better way to deliver each outcome, and executes the work end to end across every system, with every action governed. The result is measurable ROI and employees whose problems are resolved before they notice them. Thira is backed by a $21M seed round led by Madrona and led by the co-founders of Apptio, and we're building the team that will define this category.
The role
You'll design and build the core AI agentic framework powering Thira's autonomous enterprise execution engine. This isn't prompt engineering on top of an existing platform. You are architecting the orchestration layer, memory systems, and agent pipelines from scratch. You'll work directly with the CTO and have outsized influence on technical direction, owning a significant chunk of the full agentic stack from day one and setting the tone for our technology and culture.
What you will own
- Design and build the multi-agent orchestration layer (LangGraph, CrewAI, and the like) that detects, routes, delegates, and resolves issues autonomously.
- Implement the full episodic and semantic memory stack: vector stores, retrieval pipelines, and the feedback loop that lets agents learn from human resolutions.
- Build the MCP-based action library and third-party connectors: integrations with identity systems, SaaS tools, device-management platforms, and internal knowledge bases.
- Own the LLM evaluation framework: prompt versioning, regression testing, and model benchmarking across frontier and budget tiers.
- Architect human-in-the-loop approval flows with structured JSON extraction, retry logic, and graceful fallback to human agents.
- Instrument agent traces, latency, and resolution-rate metrics so the team can iterate fast with data.
What we are looking for
- 3+ years building production AI/ML systems: not notebooks, but shipped code handling real traffic.
- Hands-on experience designing multi-step LLM pipelines with tool use, structured outputs, and retry/parsing patterns.
- Deep understanding of RAG architectures: chunking strategies, embedding models, hybrid retrieval, and re-ranking.
- Fluency in Java, Python async patterns, REST API design, and Pydantic schema validation.
- Strong instincts for eval-driven development: you write test cases before you tune prompts.
- Comfortable operating in a 0→1 environment with minimal process and high ambiguity.
Strong plusses
- Experience with ITSM, enterprise SaaS, or IT operations tooling (ServiceNow, Jira Service Management, Freshservice).
- Experience building an agentic harness for governance.
- Prior work on agent memory systems or long-horizon task completion with LLMs.
- LLMOps tooling: Langfuse, OpenTelemetry, or Arize Phoenix for observability and tracing.
- Familiarity with open-weight models (Llama, Mistral, Qwen) and when to use them over frontier APIs.
Location
Bellevue, WA
How to apply
To apply, email us and tell us where you have done this before, why Thira, and a few links. We read every application.