Tech Lead – Vision-Language Modeling for Radiology

floy.com; Connecticut; Remote; EUR 80,000 - 120,000; Full time

Job summary

Join a pioneering team dedicated to revolutionizing medical diagnostics through advanced AI. This role offers the opportunity to lead a talented R&D team focused on developing cutting-edge Vision-Language Models and Large Language Models tailored for radiology. You'll be at the forefront of multimodal AI, translating research into impactful clinical applications. With a mission-driven culture and a commitment to innovation, this position not only supports personal growth but also contributes to improving patient outcomes in often overlooked areas of healthcare. If you're passionate about AI and eager to make a difference, this is the role for you.

Benefits

Flexible remote work culture

Company retreats

Publication and patent opportunities

Collaborative environment

High-impact research opportunities

Qualifications

• Experience in building advanced Vision-Language Models or Large Language Models.
• Strong proficiency in Python and deep learning frameworks like PyTorch or TensorFlow.

Responsibilities

• Lead initiatives with cross-functional teams ensuring clinically relevant research.
• Design and optimize Vision-Language and LLM architectures for radiology.

Skills

Machine Learning

Vision-Language Models

Large Language Models

Python

Communication Skills

Attention Mechanisms

Transformers

Multimodal Fusion Methods

Education

PhD in Computer Science

Master’s in Machine Learning

Tools

PyTorch

TensorFlow

DICOM

NIFTI

Job description

Tech Lead – Vision-Language Modeling for Radiology

Permanent employee, Full-time · Remote, Munich

Your mission

We’re seeking a highly skilled and experienced ML Research Engineer with a proven track record in building advanced Vision-Language Models (VLMs) or Large Language Models (LLMs).

Floy is supporting radiologists by boosting their diagnostics efforts with unconventional AI products focused on overlooked diseases. You will lead an R&D team dedicated to pushing the frontier of multimodal AI, from initial concept to clinical release. Publications and patents are highly encouraged and actively supported.

Your responsibilities

1. Lead cross-functional initiatives with radiologists, biologists, and software engineers, ensuring research is clinically relevant and deployed effectively.

2. Design, implement, and optimize cutting-edge Vision-Language and LLM architectures tailored for radiology reports.

3. Generate IP by pushing beyond published SOTA in computer vision, medical imaging, and LLMs.

4. Curate, preprocess, and manage complex radiological datasets (DICOM, NIFTI, etc.) at scale, ensuring reproducibility and regulatory compliance.

5. Employ best practices in MLOps for seamless data pipelines, experiment tracking, and continuous model delivery.

6. Remain up-to-date on the latest breakthroughs in multimodal learning, large-scale language modeling, and medical image processing.

7. Translate emerging academic research into robust, real-world clinical applications.

8. Mentor junior team members and foster a culture of scientific rigor, creativity, and relentless curiosity.

What are we looking for?

1. PhD in Computer Science, Machine Learning, or a related field or Master’s with significant industry experience.

2. Must have built, deployed, or significantly contributed to LLM or Vision-Language architectures in production (e.g., GPT-based models, BLIP, CLIP, RAG pipelines).

3. Strong grasp of attention mechanisms, Transformers, and multimodal fusion methods.

4. Proven expertise in Python with deep proficiency using PyTorch or TensorFlow.

5. Solid understanding of distributed training, GPU acceleration, and HPC environments.

6. Track record of peer-reviewed publications at renowned ML/CV/NLP conferences (NeurIPS, ICLR, ICML, CVPR, ICCV, ECCV, ACL, EMNLP, NAACL) or leading scientific journals.

7. Experience working with large and uncleaned data.

8. Strong written and verbal communication skills in English, capable of translating complex research.

Good-to-have:

1. Experience with volumetric medical imaging (CT/MRI) and biological contexts to interpret organ pathologies.

2. Experience working with medical experts and medical background knowledge.

3. Basic German skills to understand radiology reports.

4. Exposure to data engineering and MLOps.

We are looking for brilliant, hard-working people who strive to become recognised thought leaders in their domain. If you enjoy learning new things and thrive in a fast-paced environment, we would love to meet you. Together, we will continuously tailor the role to your strengths and development goals.

Why us

Pioneer medical AI to maximize human health. Become part of an ambitious team valuing individuals, dedication, and a joyful work experience. Solve novel challenges with life-saving implications:

• High-Impact Research: See your work transition from cutting-edge prototypes into life-saving clinical tools.

• Publication and Patent Opportunities: We encourage you to publish in top venues and generate patents that push the field forward.

• Collaborative Environment: Engage with a world-class team of ML engineers, radiologists, data scientists, and product managers.

• Mission-Driven Culture: Contribute to improving patient outcomes on conditions often overlooked by mainstream research.

Remote team: We provide flexible remote team culture, company retreats, and fair compensation.

Floy is on a mission to build the infrastructure for personalized health. Today, our AI products help radiologists to detect typically overlooked diseases. We envision a future where everybody can access annual holistic health assessments to prevent diseases through early detection.

Floy was founded in June 2021 and raised 8.8m€ total funding from Europe’s leading investors. Over the last months, the team grew to 45 exceptional people. Our pace only accelerates from here.