G2i Inc.
AI Engineer, Agents & Search
- Compensation
- $170K–$230K / yr
- From job posting
- Location
- LATAM
- Employment type
- Full-time
- Posted
- 22 September 2026 (8 days ago)
Checked 8 days agoApplications go to the employer, never to RoleSprint
About this role
Employment: Full-time, direct hire Location: Remote — United States or Latin America US compensation: $170,000–$230,000+ annual base, depending on experience and scope. Flexibility toward the higher end for the right staff-level engineer. LATAM compensation: A separate, lower regional range applies and will be discussed during the recruiting process.
ABOUT OUR CLIENT
Our client builds AI-powered software for healthcare staffing. Its platform helps recruiters find healthcare providers, personalize outreach, manage ongoing conversations, and connect interested providers with relevant opportunities.
ABOUT THE ROLE
Our client is looking for an AI Engineer to build and operate production agent systems, with a focus on agent orchestration, search, retrieval, and evaluation.
You’ll develop the backend systems that allow agents to use tools, retrieve relevant information, maintain state, and complete workflows reliably. You should be comfortable taking systems from implementation through production operation and using repeatable evaluations to determine whether changes actually improve results.
WHAT YOU’LL DO
- Build and improve production LLM agents and the orchestration layer that controls their execution.
- Design tool-calling systems, including tool interfaces, validation, error handling, and recovery.
- Develop retrieval pipelines combining structured filters, keyword search, embeddings, and reranking.
- Build repeatable evaluations and experiments to measure agent behavior, retrieval quality, and regressions.
- Implement durable, asynchronous workflows that handle retries, interruptions, and long-running tasks.
- Investigate production failures and improve reliability, latency, cost, and observability.
- Apply strong backend engineering practices to AI features used in real recruiting workflows.
WHAT WE’RE LOOKING FOR
- Hands-on experience building, deploying, and operating LLM agent systems used in production.
- Strong backend engineering fundamentals, with TypeScript experience or proficiency in an equivalent backend language.
- Practical experience designing agent orchestration or harnesses, including execution control, state management, and tool use.
- Experience with RAG or search systems and an understanding of how filtering, keyword retrieval, embeddings, and reranking work together.
- Experience building repeatable evaluations, comparing approaches, and identifying meaningful improvements.
- Experience with asynchronous processing and reliable workflows.
- Ability to explain architectural decisions, production failures, and the trade-offs behind your solutions.
NICE TO HAVE
- Experience in healthcare, staffing, recruiting technology, or related workflows.
- Staff-level technical ownership across architecture, delivery, and production operation.
- Experience improving both retrieval quality and downstream agent task completion.
INTERVIEW PROCESS
Resume review → G2i video screen for external applicants → direct technical fit review by Fetch → interviews focused on production agent systems, orchestration, tooling, and evaluation.
Target start: Before December.
Work location
- LATAM
Related jobs
Ready to make a decision?
This role is either worth your time or it isn’t.
Analyze the posting against your experience, see the gaps clearly, and build the right materials only if the opportunity makes sense.
Nothing is submitted automatically. You choose what happens next.
About this listing
Published on Ashby under the board identifier G2i, which is the name the employer’s own job board carries. RoleSprint has not verified the company’s registered or trading name, so it is shown exactly as published rather than tidied up.
RoleSprint is not the employer and not a recruiter. Applications are made on the employer’s own site and never reach us; what RoleSprint does is help you decide whether a role is worth your time and prepare for it if it is.
Published 22 September 2026, last checked 8 days ago. A posting stops being advertised here 90 days after the employer published it, and one the employer takes down is marked closed rather than quietly removed.