AI Machine Learning and Data Augmentation, Senior Scientist

Company: SystImmune Inc.
Location: Redmond
Posted on: April 5, 2025

Job Description:

SystImmune Inc. is a clinical-stage bio-pharmaceutical company dedicated to developing innovative treatments for cancer through breakthrough-therapeutic multi-specific antibodies and antibody-drug conjugates (ADCs). With eight assets in ongoing clinical trials and a robust preclinical pipeline, we are seeking a talented Senior Scientist/Programmer in our AI Drug Design (AIDD) team to lead the extension of our in-house implementation of large language model (LLM), focusing on sequence-to-structure-to-activity relationship modeling for antibody discovery, protein engineering, and immunology oncology applications.Job Summary:We are looking for an exceptional Senior Scientist/Programmer to drive innovation and optimization in our AI capabilities, leveraging our internal data and expertise in antibody discovery, protein engineering, and immunology oncology. The successful candidate will design, develop, and implement AI models, data pipelines, and parallel computing architectures to accelerate the discovery and development of novel therapeutics using our in-house LLM implementation.Key Responsibilities:

• Llama 3.3 Implementation and Extension:
  • Develop and fine-tune Llama 3.3 models for sequence-to-structure-to-activity relationship prediction, leveraging internal data from antibody discovery, protein engineering, and immunology oncology projects.
  • Integrate domain-specific knowledge and constraints into the Llama 3.3 framework to improve model performance and accuracy.
  • Data Generation and Processing:
    • Design and implement data generation pipelines to produce high-quality training datasets for Llama 3.3 models, including sequence, structure, and activity data from internal projects.
    • Develop and optimize algorithms for data processing, feature extraction, and data augmentation to support Llama 3.3 model development.
    • Fine-Tuning of AI Model with Processed SI R&D Data:
      • Fine-tune the Llama 3.3 model using processed SystImmune R&D data, including antibody discovery, protein engineering, and immunology oncology datasets.
      • Integrate additional features and constraints from SystImmune's internal data to improve model performance and accuracy.
      • Embedding Language Models for New Data Structure Design:
        • Embed language models (e.g., Milvus, LangChain) to convert data into numerical representations and store it in a vector database for new data structure design, mining, and processing.
        • Utilize RAG (Retrieval-Augmented Generator) with MariaDB Vector DB to enhance data retrieval and generation capabilities.
        • Automatic Data Flow Management:
          • Design and implement automatic data flow management from current LIMS (Laboratory Information Management System) MariaDB to AI Embedding DB, ensuring seamless data integration and synchronization.
          • Develop data pipelines to extract, transform, and load data from various sources into the AI Embedding DB.
          • Parallel Computing and Optimization:
            • Implement parallel computing architectures using technologies such as MPI, OpenMP, or distributed computing frameworks (e.g., Dask, Ray) to accelerate Llama 3.3 model training and inference.
            • Optimize code performance on various computing platforms, including CPUs, GPUs, and high-performance computing clusters.
            • Software Development and Integration:
              • Design, develop, and maintain software applications and tools for Llama 3.3 model training, data processing, and parallel computing, using languages such as Python, C++, or Julia.
              • Collaborate with our AIDD team to ensure seamless integration of Llama 3.3 workflows into our production environment.
              • Data Security and Backup Management:
                • Develop and implement robust data security measures to protect sensitive external data, including encryption, access controls, and authentication protocols.
                • Design and manage backup strategies for external data, ensuring data integrity, redundancy, and recoverability in case of data loss or corruption.
                • Collaborate with IT and cybersecurity teams to ensure compliance with organizational data security policies and regulatory requirements (e.g., GDPR, HIPAA).
                • Conduct regular security audits and risk assessments to identify potential vulnerabilities and implement corrective measures.
                • Data Loss Prevention and Incident Response:
                  • Develop and implement procedures for preventing data loss and responding to potential security incidents, including data breaches or unauthorized access.
                  • Establish a disaster recovery plan to ensure business continuity in case of data loss or system downtime.Requirements:
                    • Education:Ph.D. or Master's degree in Computer Science, Artificial Intelligence, Bioinformatics, Computational Biology, or related field.
                    • Experience:3+ years of experience in AI/ML model development, with a focus on natural language processing and/or database management.
                    • Technical Skills:
                      • Proficiency in Python, C++, or Julia programming languages.
                      • Experience with deep learning frameworks such as PyTorch or TensorFlow.
                      • Familiarity with parallel computing architectures and distributed computing frameworks.
                      • Data Security and Backup Management.
                      • Domain Knowledge:Strong understanding of antibody discovery, protein engineering, and immunology oncology principles, as well as experience working with internal data from these fields.
                      • Communication Skills:Excellent communication and collaboration skills, with the ability to work effectively with cross-functional teams.Nice to Have:
                        • Experience with Llama 3.3 or other large language models.
                        • Experience with RAG (Retrieval-Augmented Generator) and MariaDB Vector DB.
                        • Knowledge of process development principles and their application in biopharma manufacturing.
                        • Experience with Milvus, LangChain, or other vector databases.Compensation and Benefits:The hiring pay range for this position is $150,000 - $250,000 per year based on skills, education, and experience relevant to the role.SystImmune is a leading and well-funded clinical-stage biopharmaceutical company located in Redmond, WA and Princeton, NJ. It specializes in developing innovative cancer treatments using its established drug development platforms, focusing on bi-specific, multi-specific antibodies, and antibody-drug conjugates (ADCs). SystImmune has multiple assets in various stages of clinical trials for solid tumor and hematologic indications. Alongside ongoing clinical trials, SystImmune has a robust preclinical pipeline of potential cancer therapeutics in the discovery or IND-enabling stages, representing cutting-edge biologics development.We offer an opportunity for you to learn and grow while making significant contributions to the company's success. SystImmune offers a comprehensive benefits package.SystImmune is an Equal Opportunity Employer. We welcome diverse talent and encourage all qualified applicants to apply.
                          #J-18808-Ljbffr

Keywords: SystImmune Inc., Bellevue , AI Machine Learning and Data Augmentation, Senior Scientist, Other , Redmond, Washington