Generative AI Engineer

About BostonGene

Since our inception in Boston in 2015, we've led the charge in oncology personal healthcare, offering an extensive array of diagnostic tools that empower clinical decisions and advance patient care. Our culture is our foundation—fueled by innovation, a commitment to transformation, and a team of authentic, driven individuals worldwide. At BostonGene, you'll find a community that's not just about the work but about making a difference, together. Join us to be a part of a future where your work contributes to transformative cancer treatments and shapes the lives of patients globally. We develop a distributed information and analytical system that provides oncologists with the necessary data for diagnosis and personalized treatment of patients.

Position Summary

We are seeking a Generative AI Engineer to specialize in biological data, including RNA-seq, Digital Pathology (Multiplexed Immunofluorescence, Hematoxylin, and Eosin staining) and other types of biological data. In this role, you will develop and implement single-modality encoders (e.g., VAE, LIAE, DINOv2) and multimodal deep learning models (e.g., Stable Diffusion based and/or DDPM) using this data. The position also involves interpreting complex biological data and ensuring adherence to Good Clinical Practice (GCP) and Good Laboratory Practice (GCLP) standards.

Job responsibilities

• Analyze and interpret single-modality data, including, but not limited to RNAseq, histology, cfRNA, and xCR.

• Develop and implement Python-based computer vision algorithms for image analysis, encompassing data preprocessing, image segmentation, feature extraction, and classification.

• Maintain detailed records of all analyses to ensure data integrity and reproducibility.

• Stay updated with the latest advancements in computer vision, imaging, and deep learning technologies.

• Ensure all activities comply with GCP and GCLP standards.

• Integrate with LLM API for process automation and support.

• Support and develop multimodal diffusion-based models.

Required qualifications

• Bachelor’s, preferably Master’s or PhD degree in Computer Science, Bioinformatics, Biomedical Engineering, or a related field.

• At least 2 years of experience in computer vision or a related field.

• Demonstrated experience with Python-based image analysis and computer vision algorithms.

• Strong analytical and problem-solving skills.

• Good communication skills, both written and verbal.

• Ability to work collaboratively in a multidisciplinary team.

• Attention to detail and a commitment to producing high-quality work.

Required Technical Skills

• Proficiency in Python programming language.

• Strong understanding of computer vision concepts, including image processing, segmentation, and feature extraction. OR

• Demonstrated experience processing xCR data. OR

• Experience processing RNA sequencing data.

• Experience with libraries such as OpenCV, scikit-image, and PyTorch. (PyTorch is a main framework used by division).

• Familiarity with image analysis techniques used in biological and medical research.

• Knowledge of machine learning algorithms and their application to data.

• Ability to handle large datasets and perform statistical analysis.

• Proficiency in using data visualization tools such as Matplotlib, Seaborn, or similar.

• Understanding of LLM principles of work and experience in LLM integration with API OR

• Understanding of stable diffusion principles of work. Experience with multimodal models.

What we offer:

• Relocation support.

• Comfortable office in the center of Yerevan, next to "Druzhba" metro station.

• Health insurance (comprehensive coverage including medical, dental, and vision plans).

• Flexible / hybrid work options (hybrid format, flexible hours).

• Professional development (support for trainings, workshops, conferences, and further education).

• Business trips (opportunities to build partnerships, attend conferences, and support the company's global presence).

• Staff referral program (bonuses for referring suitable candidates).

• Meals (free or subsidized meals, snacks, and beverages at the workplace).