Computational Biologist (AI/ML) - Essex Management

Emmes Group•Rockville, MD

4d•Remote

About The Position

This position supports "Essex, an Emmes Company". Essex is a biomedical informatics and health information technology-focused consultancy founded in 2009 and headquartered in Rockville, MD. The Essex team comprises experts with extensive experience in strategically developing and managing complex health and biomedical information programs for clients in the Federal Government, research academia, and private sectors. The Computational Biologist (AI/ML) is a role within the Bioinformatics Department of the BIDS Division at Essex. This role brings meaningful scientific and technical expertise to the design, execution, and delivery of bioinformatics work across federal biomedical research programs. The Computational Biologist (AI/ML) owns well-defined tasks and small projects with minimal supervision and contributes substantively to team problem-solving and scientific quality. This role specifically focuses on applying Artificial Intelligence, Machine Learning and Deep Learning to bioinformatic analysis, and thus the ideal candidate is expected to leverage traditional bioinformatic techniques as well as emerging techniques. Essex supports programs in precision oncology, cancer genomics, clinical data infrastructure, and translational research, and the Computational Biologist (AI/ML) is expected to bring scientific judgment and technical capability to the work, not just execution.

Requirements

Working proficiency in the core technical tools, analytical approaches, and data standards relevant to the assigned program and department.
Ability to work independently and within a team in a fast-paced, collaborative environment.
Strong written and oral communication skills, including the ability to document work clearly and present findings to technical audiences.
Proficiency with Microsoft Office applications.
Proficiency in Python and SQL; demonstrated experience with ML frameworks (PyTorch, TensorFlow) and code versioning (Git).
Strong background in machine learning and AI, including deep learning architectures (CNNs, GNNs) applied to biomedical or complex multi-modal datasets.
Familiarity with genetic variant standards (HGVS, VCF) and clinical data ontologies.
Demonstrated ability to work cross-functionally and communicate technical results clearly to diverse scientific and clinical audiences.
Bachelor's degree or advanced degree in bioinformatics, computational biology, data science, genetics, biology, health informatics, clinical research, or a related field.
2 to 5 years of relevant professional or research experience.
Demonstrated success applying AI/ML to biomedical or multi-modal datasets (genomics, proteomics, clinical).

Nice To Haves

Track record of publications or applied innovation in AI-driven data science for life sciences preferred.
Experience applying LLMs or RAG approaches to scientific or clinical data problems preferred.

Responsibilities

Own and execute well-defined analytical and technical tasks and small projects with minimal supervision from senior staff or your manager.
Assist Associate Informaticists with task-related questions, troubleshooting, and orientation.
Contribute substantively to team discussions on methodology, standards, tools, and technical decisions.
Apply working familiarity with best practices in your domain to deliver scientifically sound, high-quality work products.
Support peer review of deliverables and contribute to quality assurance activities.
Contribute to team documentation, SOPs, and knowledge base materials.
Shadow senior staff during candidate interviews to begin developing evaluation skills.
Participate in internal training sessions, brown bags, and knowledge-sharing activities.
Perform other related duties as assigned.
Design and implement AI/ML models applied to biomedical data, including genomic, proteomic, and multimodal clinical datasets, to support precision oncology and translational research.
Apply large language models, retrieval-augmented generation (RAG) techniques, and graph neural networks to make biomedical data interoperable and AI-ready.
Develop, test, and optimize pipelines for variant calling and annotation leveraging modern ML workflows and frameworks.
Curate, model, and integrate genetic and clinical datasets into standardized, interoperable formats to support precision medicine programs.
Generate high-quality, interpretable reports for internal and external stakeholders that translate complex AI/ML outputs into actionable scientific and clinical insights.