Artificial Intelligence Engineer – Clinical NLP & LLMs

About the role

An enterprise AI platform running entirely inside its own data center, with no patient data leaving the hospital, supports clinicians and finance teams in real time within the hospital information system. The role builds and deploys clinical NLP and LLM models for radiology quality control, decision support, closed-loop follow-up and medical billing.

Key responsibilities

• Build and fine-tune Turkish clinical NLP models: encoder classifiers, NER, assertion and negation detection, and LLMs.
• Serve open-weight LLMs on-premise (vLLM / SGLang / TensorRT-LLM) on NVIDIA GPUs, using FP8/FP4 quantization and strict latency budgets.
• Design evaluation pipelines: blind gold sets, shadow mode, inter-annotator agreement and regression tests.
• Work with radiologists and clinicians on labeling, and with the hospital information system team on integration (REST, CDC / Kafka, read replicas).
• Build RAG pipelines over medical guidelines (Qdrant / Milvus).

Required profile

• 3+ years of hands-on ML/NLP experience, with strong Python and PyTorch / Hugging Face skills.
• Experience deploying LLMs in production; low-latency serving and GPU optimization are a big plus.
• Solid understanding of evaluation methodology, with attention to false positives as well as accuracy.
• Experience with Turkish NLP, or the motivation to master it.
• Comfort with Linux, Docker and on-prem infrastructure.
• Strong sense of responsibility for data privacy and security.

Nice to have

• Healthcare data experience (HL7 / FHIR, HIS / HBYS, PACS, clinical terminologies).
• Speech technologies (Whisper STT / TTS), OCR and document understanding.
• Kafka / CDC, rule engines, MLOps.

The application process is handled confidentially, and applications are sent by LinkedIn or by email with CV and GitHub or portfolio.