Senior AI Engineer — Production LLMs (Remote)

Orbitant; Spain (TX); On-site; USD 46,000 - 69,000; Full time

Benefits offered by this job

Top office in Madrid with free attend.

Flexible benefits with health options

Training and mentoring

Job summary

Orbitant is seeking AI Engineers (mid and senior) to design production-grade LLM-powered systems. This remote role focuses on delivering real business impact and scalable, maintainable solutions.

You will design, implement, and ship AI agents and RAG pipelines for international clients, with emphasis on cost, latency, and observability. Ideal candidates have strong Python, hands-on orchestration experience, and a passion for practical, value-driven AI.

Qualifications

• Experience building production systems with LLMs: agents, RAG, and generation pipelines.
• Strong Python as primary language.
• Hands-on knowledge of an agent/workflow orchestration framework (e.g. LangGraph, LangChain).
• Experience evaluating and tracing LLM-based systems (Langfuse or similar).
• Solid prompt engineering knowledge.
• Experience with Vector DBs and RAG patterns.
• Ability to reason about cost, latency, and model trade-offs.
• Proficiency in English for international collaboration.

Responsibilities

• Design, build, and productionize AI agents and LLM-based systems.
• Take projects from pilot to production with measurable outcomes.
• Implement and maintain RAG systems over client documentation and knowledge.
• Design multi-step agent/workflow architectures and handle cost management.
• Build evals (offline and online) with tooling like Langfuse.
• Contribute to Orbitant's internal AI-first platform with reusable components.

Skills

LLM production systems

Python programming

English communication

Prompt engineering

System design

Tools

Python

LangGraph

LangChain

Langfuse

Vector DBs

Job description

Orbitant is seeking AI Engineers (mid and senior) to design production-grade LLM-powered systems. This remote role focuses on delivering real business impact and scalable, maintainable solutions.

You will design, implement, and ship AI agents and RAG pipelines for international clients, with emphasis on cost, latency, and observability. Ideal candidates have strong Python, hands-on orchestration experience, and a passion for practical, value-driven AI.