Data Scientist - AI-Powered Biomedical Data Analysis - DSHR
- NavitsPartners
- New York, New York
- Full Time
Data Scientist - AI-Powered Biomedical Data Analysis - DSHR
Job Title: Data Scientist - AI-Powered Biomedical Data Analysis
Location: Bronx, NY 10458 (Hybrid)
Job Type: 1-Year Contract (with potential for extension)
About the Role:
We are seeking an experienced and innovative Data Scientist to lead the development and deployment of AI-driven solutions for biomedical literature and synthetic data analysis. This hybrid role is based in the Bronx, NY, and offers the opportunity to contribute to cutting-edge research at the intersection of artificial intelligence, life sciences, and healthcare.
The successful candidate will work on designing and optimizing scalable AI models using open-source large language models (LLMs) to classify biomedical literature across multiple dimensions. This role plays a key part in generating insights that support evidence synthesis, systematic reviews, and clinical research.
Key Responsibilities:
Design and refine multi-dimensional classification frameworks (e.g., relevance, data type, medical category, application area)
Implement Chain-of-Thought (CoT) reasoning and Few-Shot Learning (FSL) techniques
Deploy and optimize open-source LLMs (e.g., LLaMA) for high-throughput biomedical text classification
Perform inference on 5,000+ biomedical abstracts with attention to performance and accuracy
fine-tuning or low-rank adaptation (LoRA) for domain-specific model enhancement
Curate high-quality training/validation datasets in collaboration with biomedical domain experts
Standardize data preprocessing workflows to ensure consistency and integrity across datasets
Identify trends in synthetic biomedical data applications, including methodology, disease focus, and clinical relevance
Manage batch processing pipelines for large-scale text analysis using GPU-enabled infrastructure
Present findings through reports, dashboards, and scientific presentations
Required Qualifications:
Master's or PhD in Computer Science, Data Science, Biomedical Informatics, or related field
3+ years of experience in AI/ML projects, especially NLP and text classification
Strong programming skills in Python
Proficiency with machine learning libraries (e.g., PyTorch, TensorFlow)
Experience with open-source LLMs (e.g., LLaMA, GPT)
Knowledge of advanced prompting methods, such as CoT and FSL
Ability to communicate effectively with both technical and non-technical stakeholders
Strong problem-solving mindset and adaptability in a fast-paced R D environment
Preferred Skills:
Familiarity with biomedical ontologies and data standards
Experience with GPU-based model training and inference
Knowledge of tools for data pipeline orchestration and high-throughput processing
Prior work with systematic reviews, evidence synthesis, or literature mining
Data Scientist - AI-Powered Biomedical Data Analysis - DSHR
NavitsPartners
New York
Full Time
Published on 05/31/2025
Job Title: Data Scientist - AI-Powered Biomedical Data Analysis
Location: Bronx, NY 10458 (Hybrid)
Job Type: 1-Year Contract (with potential for extension)
About the Role:
We are seeking an experienced and innovative Data Scientist to lead the development and deployment of AI-driven solutions for biomedical literature and synthetic data analysis. This hybrid role is based in the Bronx, NY, and offers the opportunity to contribute to cutting-edge research at the intersection of artificial intelligence, life sciences, and healthcare.
The successful candidate will work on designing and optimizing scalable AI models using open-source large language models (LLMs) to classify biomedical literature across multiple dimensions. This role plays a key part in generating insights that support evidence synthesis, systematic reviews, and clinical research.
Key Responsibilities:
Design and refine multi-dimensional classification frameworks (e.g., relevance, data type, medical category, application area)
Implement Chain-of-Thought (CoT) reasoning and Few-Shot Learning (FSL) techniques
Deploy and optimize open-source LLMs (e.g., LLaMA) for high-throughput biomedical text classification
Perform inference on 5,000+ biomedical abstracts with attention to performance and accuracy
fine-tuning or low-rank adaptation (LoRA) for domain-specific model enhancement
Curate high-quality training/validation datasets in collaboration with biomedical domain experts
Standardize data preprocessing workflows to ensure consistency and integrity across datasets
Identify trends in synthetic biomedical data applications, including methodology, disease focus, and clinical relevance
Manage batch processing pipelines for large-scale text analysis using GPU-enabled infrastructure
Present findings through reports, dashboards, and scientific presentations
Required Qualifications:
Master's or PhD in Computer Science, Data Science, Biomedical Informatics, or related field
3+ years of experience in AI/ML projects, especially NLP and text classification
Strong programming skills in Python
Proficiency with machine learning libraries (e.g., PyTorch, TensorFlow)
Experience with open-source LLMs (e.g., LLaMA, GPT)
Knowledge of advanced prompting methods, such as CoT and FSL
Ability to communicate effectively with both technical and non-technical stakeholders
Strong problem-solving mindset and adaptability in a fast-paced R D environment
Preferred Skills:
Familiarity with biomedical ontologies and data standards
Experience with GPU-based model training and inference
Knowledge of tools for data pipeline orchestration and high-throughput processing
Prior work with systematic reviews, evidence synthesis, or literature mining
Data Scientist - AI-Powered Biomedical Data Analysis - DSHR
NavitsPartners
New York
Full Time
Published on 05/31/2025
Job ID: 479550131
Originally Posted on: 6/3/2025
Want to find more Chemistry opportunities?
Check out the 17,602 verified Chemistry jobs on iHireChemists
Similar Jobs
Sign Up for Job Alerts
