AI Engineer

We are seeking an AI Engineer specializing in LLMs to help build, evaluate, and ship production-grade generative AI systems. In this role, you will independently deliver LLM features, from prototype to production, applying solid engineering and evaluation practices, and growing toward end-to-end ownership of larger, more ambiguous problems.

Build and ship LLM-powered application features (chatbots, copilots, agents, internal tools), combining components like RAG pipelines, agents, and APIs.

Run and extend LLM evaluations (evals) for the systems you build, using and improving existing gold-standard datasets and benchmarks, implementing automated eval checks and scoring, and applying defined metrics for factuality, grounding, robustness, and user impact.

Diagnose and resolve failure modes (hallucinations, retrieval issues, tool-use errors).

Apply advanced prompt engineering techniques and follow prompt versioning and lifecycle practices.

Incorporate latency, cost, and reliability in your implementation choices, and consider production trade-offs.

Collaborate cross-functionally with engineers, product, data, and design to deliver the right solutions.

Follow established practices for responsible AI, including safety, PII handling, and observability.

3+ years of experience in software engineering, machine learning, or applied AI, with a track record of delivering features to completion.

Solid software engineering fundamentals (testing, modular design) in Python.

Experience taking AI or LLM-powered features from concept through deployment, and contributing to their ongoing maintenance.

Familiarity with automated testing strategies for non-deterministic systems, and sound debugging and analytical skills for investigating ambiguous model behavior.

A working understanding of prompt engineering and prompt lifecycle management, RAG architectures and retrieval evaluation, and common LLM limitations and failure patterns.

Experience using Data Analytics techniques (SQL, analysis, and visualization) to inform product decisions and delivery.

A product mindset and a genuine interest in understanding our product and customer needs to build the right solutions.

The ability to independently drive work to completion, and to know when to seek guidance on ambiguity.

Clear communication of trade-offs, risks, and system performance, including the uncertainty inherent in AI systems, to your team and stakeholders.

 

Experience contributing to ambiguous projects and communicating technical risks to stakeholders.

Exposure to production-grade evaluation using more advanced metrics and statistical validation.

Hands-on experience with model fine-tuning, adversarial red-teaming, or safety testing.

 

🏠 Remote Flexibility: The freedom to work from home any day that works for you.

🌴 Time to Recharge: 25 working days of paid vacation and Jornada Intensiva in August..

💊 Alan Health Insurance: Premium health, dental, and mental health support via Alan. Pre-existing conditions are covered.

😋 Meal Perk: €150/month allowance on your Alan card + 50% off Ametller Origen prepared dishes at the office.

💸 Tax-Free Savings: Increase your take-home pay by using Flexible Remuneration for extra meal costs (up to €70/mo) and public transport (up to €136/mo).

🖥️ Home Office Gear: We provide a table, ergonomic chair, and monitor for your home setup.

🇪🇸 Language Learning: Free Spanish classes.

🤑 Referrals: Cash rewards for bringing in new talent. 

🌟 Social Life: Daily office breakfast and monthly team events

🎯 Dynamic Hub: A high-energy, inclusive environment designed for collaboration and connection with a team that represents over 60 countries.

*Benefits offered may differ based on the type of contract that is issued

 

So, what are you waiting for? Apply now!

All applications and CVs must be submitted in English 😉