Join our team to develop and validate advanced AI/ML models addressing complex challenges in life science R&D areas such as target choice, patient identification, molecule design and clinical trial effectiveness. Design and implement AI/ML pipelines for rapid experimental iteration, including classical ML models and advanced LLM customization techniques. Collaborate with subject matter experts and AI engineers to develop and deploy models and ensure high-quality, scientifically sound solutions.

Responsibilities:

• Develop and validate advanced AI/ML models to tackle complex problems in target choice, patient identification, molecule design/chemistry, manufacturing and controls (CMC), and clinical trial effectiveness.

• Design and implement AI/ML pipelines for data preprocessing, feature engineering, model training, hyperparameter tuning, and model evaluation, enabling rapid experimental iteration and adhering to industry’s best practices in MLOps.

• Besides classical ML models fine-tuning (i.e., support vector machine and random forest), this team is also responsible for large language model (LLM) customization and fine-tuning using complex techniques (i.e., low-rank adaptation (LoRA) and reinforcement learning (RL) with human feedback).

• Collaborate with AI engineers to deploy AI/ML models in both classical inference pipelines and agentic framework approaches.

• Collaborate with subject matter experts in pre-clinical research, clinical trial design and operation, precision medicine, regulatory science, and CMC to guarantee scientifically sound and high-quality simulation modeling and analytical solutions.

Why You?

Basic Qualifications:

• BS degree in computer science, bioinformatics, applied math, statistics or engineering  

• 4+ years of data science and machine learning developer experience

• Experience working with LLM technologies, including developing generative and embedding techniques, modern model architectures, retrieval-augmented generation (RAG), fine tuning / pre-training LLM (including parameter efficient fine-tuning), and evaluation benchmarks.

• Experience in data wrangling from databases for feature engineering and model training purposes.

• Experience in Python, TensorFlow/PyTorch, and scalable ML architectures.

• Experience with AI/ML model metrics (e.g., F1 and AI-contents evaluation metrics) including setting up human-in-the-loop (HITL) AI/ML monitoring.

• Coding and software engineering skills, and knowledge with software engineering principles around testing, code reviews and deployment.

Preferred Qualifications: 

• MA degree in computer science or equivalent qualitative science fields

• Experience with reinforcement learning (RL) and multi-agent framework

• Experience with graph database in the context of GraphRAG

• Experience with computer vision

• Experience designing and managing AI workloads on cloud platforms and/or high-performance computing environments

• Knowledge of cost optimization strategies for GPU computing in both cloud and on-premises scenarios

• Proficiency with distributed computing frameworks (i.e., Spark, databricks, RAPIDS.ai)

• Experience in establishing AI/ML best practices, standards, and ethics

• Experience in AI/ML applications in life science domain areas: pre-clinical research, clinical trial design and operation, precision medicine, regulatory science, and CMC.

• Strong written and verbal communication skills