Back to jobs

Applied AI Engineer - Agent Architecture

Reads like an ML Engineer role: training models and running them in production.

Pay
Pay not listedSimilar roles state $166K–$237K
Work setting
Not stated
Employment
Not stated

What you’ll work on

Full posting
  • You'll design and build the core AI agentic framework powering Thira's autonomous enterprise execution engine.

  • 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.

From the employer’s posting
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
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.
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.

What you’ll bring

All qualifications

Core experience

  • 3+ years building production AI/ML systems: not notebooks, but shipped code handling real traffic.
  • Experience with ITSM, enterprise SaaS, or IT operations tooling (ServiceNow, Jira Service Management, Freshservice).
  • Hands-on experience designing multi-step LLM pipelines with tool use, structured outputs, and retry/parsing patterns.
  • Experience building an agentic harness for governance.
  • Deep understanding of RAG architectures: chunking strategies, embedding models, hybrid retrieval, and re-ranking.
  • Familiarity with open-weight models (Llama, Mistral, Qwen) and when to use them over frontier APIs.
Qualification wording
3+ years building production AI/ML systems: not notebooks, but shipped code handling real traffic.
Experience with ITSM, enterprise SaaS, or IT operations tooling (ServiceNow, Jira Service Management, Freshservice).
Hands-on experience designing multi-step LLM pipelines with tool use, structured outputs, and retry/parsing patterns.
Experience building an agentic harness for governance.
Deep understanding of RAG architectures: chunking strategies, embedding models, hybrid retrieval, and re-ranking.
Familiarity with open-weight models (Llama, Mistral, Qwen) and when to use them over frontier APIs.

About Thira

Thira is the CIO's trusted agentic AI platform that continuously learns and executes repetitive IT work.

In the employer’s words · Read in context

Apply at Thira

Posting record

Report an error

Actively hiringFirst seen by us 7 days ago, still listed, and not a repost of an earlier posting.

Status in our records
Live
First seen by us
Nov 10, 20267 days ago
Recorded sightings
7
Last seen by us
Nov 17, 2026

These dates show when we found the posting. Check the employer’s website to confirm it is still accepting applications.

How this job compares

Pay

$166K–$237K is typical

The middle half of what similar US postings state. This one doesn’t list pay.

From 1,505 postings in the last year. Stated ranges, not salaries paid.

Time since we first saw it

Day 7

Similar jobs usually come down between day 7 and day 76.

From 5,756 similar postings that came down. Coming down is not always a hire.

Thira is hiring

2 open jobs

Open jobs by the week we first saw them, last 12 weeks.

Hiring record

See how this role fits your experience

Add your resume and we’ll mark which of these tools you already use, and point out anything in the posting that could rule you out.

  • Java
  • Python
Where the posting names them
- 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.

Your next step

Complete your application on www.thira.com. The employer’s form will show what is required.

Already applied? Track this application

Job description

View original posting ↗

← All open roles Applied AI Engineer - Agent Architecture

Bellevue, WA

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.

RoleApplied AI Engineer - Agent Architecture
LocationBellevue, WA
Apply

Demand for ML Engineer roles

New ML Engineer postings at the employers we follow are up 12% over the last 6 weeks compared with the 6 before.

Weekly new ML Engineer postings at the same employers, from the week of August 17 to the week of November 9. The fewest in a week was 556, the most 1,080, and the latest week had 556.
August 17Last week

Each bar is one week of new postings. The darkest bars are the last 6 weeks.

Counted from the hiring pages we’ve followed for at least five weeks, so employers we add don’t look like growth. Updated weekly.

About the role

We file this job under ML Engineer, by the work the posting describes.

ML engineers put machine learning models into products. They write the code that trains, ships, serves and monitors models so a recommendation or prediction works for real users.

Postings ask for strong Python and software engineering, a framework such as PyTorch, cloud services, and more and more often experience with large language models.

A data scientist often works out which model to build; an ML engineer makes it run reliably in production.

US government figures for computer and information research scientists

Median yearly pay, May 2025
$140,300
Expected change, 2025 to 2035
21.8% more jobsagainst 3.5% for all jobs

The government has no code for ML engineers, so these figures are for the closest group, computer and information research scientists.

Source: US Bureau of Labor Statistics, Occupational Employment and Wage Statistics (May 2025) and Employment Projections (2025 to 2035). Occupation code 15-1221.

Source details

View original posting ↗

Source notes

Source excerpts

Selected passages from the saved posting. Check the full description for conditions and exceptions.

Pay

No pay amount identified in the saved description.

Location & working pattern

Bellevue, WA

- 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.
Work authorization

No clear work-authorization passage found. Eligibility is unconfirmed.

Find answers in the posting

AI
How answers work

AI selects complete passages from this posting. Check them for conditions and exceptions.

Uses this posting and your question. No profile needed.