Lead AI Engineer (LLMs)

About Sqilline

Sqilline Health builds Danny, an oncology analytics platform that works with real-world clinical data from 120+ hospitals in Bulgaria, Romania, Serbia, and Croatia. Pharma companies use our analyses to see how cancer treatments perform in real patients. We run our own LLMs on air-gapped infrastructure, so patient data never leaves our environment.

The Role

We are an AI-first company: LLMs read clinical records, extract the facts, and drive the analyses our data science team delivers to pharma clients. Our next step is to take these models further, with higher accuracy, honest confidence scores, and a pipeline that learns from its own mistakes. We need someone to lead that step.

This is a hands-on role with lead responsibility. You set the technical direction for how the team works with models, build the first versions yourself, and bring the team along. We care about what you have shipped with LLMs in the last year, not how many years you have on paper.

What you will do:

• Evolve our clinical extraction pipeline so the model returns one normalized value per field, a calibrated confidence score, and the source text it came from.
• Build the fine-tune feedback loop: corrected cases become training data, models retrain on a cadence, and a regression gate against a frozen gold set protects quality before any release.
• Stand up our MLOps stack from self-hosted open-source tools: annotation, data versioning, experiment tracking, evaluation, drift monitoring.
• Push automation deeper into the delivery workflow with LLM pipelines and agents, so the team spends its time on clinical judgment, not repetitive steps.
• Set the evaluation discipline: gold test sets, calibration measurement, honest metrics.
• Upskill the team. Pair with people, review their work, and run internal workshops.

What we look for:

• AI-first thinking. Your default question is “can a model do this?” and you reach for the newest tools on the market before writing another script by hand.
• You use LLMs daily in your own work: coding agents, eval suites, prompt pipelines.
• You ship. A working prototype this week beats a perfect design next quarter.
• You argue with evidence and stand your ground, including with senior people. We want someone who pushes.
• You measure. A model change without a metric behind it is not done.

Skills

You need:

• Strong Python.
• Hands-on LLM work beyond API calls: fine-tuning (LoRA/QLoRA), structured output, prompt pipelines, evaluation.
• Some MLOps exposure: experiment tracking, data versioning, or model serving.
• Comfort with Linux, Docker, and running open-source tools yourself.

Nice to have:

• Confidence calibration and applied ML statistics (ECE, reliability curves).
• vLLM or other self-hosted model serving.
• Healthcare or other regulated-data experience (GDPR, HIPAA).

What we offer:

• A challenging role in a dynamic organization.
• Competitive remuneration package.
• Comprehensive social package, including additional private health insurance and multisport card.
• A supportive, friendly, and innovative team environment.
• Opportunities for professional growth and development.

Why Join Us?

You’ll be part of a fast-growing team shaping the future of healthcare in Europe. If you love tech, thrive in dynamic environments, and want to make a real impact-this is your chance.

Apply now to learn more!