AI Engineer

Iwana Labs; United States; Remote; USD 99,000 - 166,000; Full time

Benefits offered by this job

22 days PTO

Meal allowance

Private health insurance

Learning budget

Mac workstation provided

In-person team meetups

Job summary

Iwana Labs is seeking a senior, hands-on engineer to own the systems side of production AI work. You will design agentic systems, integrate them into existing platforms, and build evaluation and observability layers that keep changes safe.

The first engagement focuses on shipping AI agents, integrating LLM capabilities into production services, and establishing release-gating practices. This remote-first role is open to candidates anywhere in Spain.

Qualifications

• Experience deploying agentic/LLM-based products to production.
• Strong foundations in scalable system design and reliability.
• Proficient in building evaluation pipelines and telemetry-driven decisions.
• Ability to collaborate with product, engineering, and data teams and drive delivery.
• Willingness to quickly learn new platforms and adapt.

Responsibilities

• Design, build, and operate AI agents and tool-calling workflows that serve real users.
• Integrate AI capabilities into existing production systems, including APIs, services, event-driven pipelines, and data platforms.
• Own the evaluation strategy, defining what good looks like, building evaluation sets, and gating releases on the results.
• Build offline and online evaluation, including regression suites, model-graded checks, human review loops, and production output sampling.
• Design agent architectures with explicit stage boundaries and bounded iteration, favouring simpler approaches where an agentic design does not earn its complexity.
• Instrument systems for quality, latency, cost, and failure modes, and implement safeguards such as validation, fallbacks, bounded retries, circuit breakers, access controls, and human approval steps.

Skills

Agentic/LLM production

Systems design

Telemetry & evaluation

Cross-functional collab

Adaptability

Tools

ML Ops

APIs & event pipelines

Job description

Role overview

A senior, hands-on engineering role owning the systems side of production AI work. The position designs agentic systems, integrates them into existing platforms, and builds the evaluation and observability layers that make ongoing change safe. The first engagement sits with a large media platform, where the focus is shipping AI agents, integrating LLM capabilities into production services, and establishing the release-gating practice.

Responsibilities

• Design, build, and operate AI agents and tool-calling workflows that serve real users.
• Integrate AI capabilities into existing production systems, including APIs, services, event-driven pipelines, and data platforms.
• Own the evaluation strategy, defining what good looks like, building evaluation sets, and gating releases on the results.
• Build offline and online evaluation, including regression suites, model-graded checks, human review loops, and production output sampling.
• Design agent architectures with explicit stage boundaries and bounded iteration, favouring simpler approaches where an agentic design does not earn its complexity.
• Instrument systems for quality, latency, cost, and failure modes, and implement safeguards such as validation, fallbacks, bounded retries, circuit breakers, access controls, and human approval steps.

Requirements

• Demonstrated experience taking agentic or LLM-based products past prototype and operating them in production.
• Strong engineering foundations and comfort owning architecture, deployment, and ongoing reliability.
• Practical ability to design and run evaluation pipelines and act on what telemetry shows.
• Skill working alongside client product, engineering, and data teams, translating needs into technical designs and leading delivery through to handover.
• Willingness to learn new platforms quickly; familiarity with a specific stack is less important than adaptability.

Benefits and work setup

Remote-first anywhere in Spain, with the team gathering in person a few times a year. Twenty-two days of paid time off plus public holidays, a meal allowance, and private health insurance. A learning budget covers conferences, courses, and books, and a Mac plus the rest of the workstation is provided. Access to current AI agents and tooling is included.