Software Engineer – Agentic Data Pipelines

This is a fully remote position, open to applicants in United States.

📋 Description

• Design, develop, and maintain agent-based systems that transform biomedical data-source references into reviewed and version-controlled datasets.

• Create LLM-driven pipelines for data sanitization, normalization, and formatting across molecular, genomic, clinical, and literature datasets.

• Establish automated quality-control processes to identify anomalies, highlight inconsistencies, and uphold data standards.

• Assess and refine agent architectures, prompting methodologies, tool specifications, validation cycles, and evaluation frameworks.

• Partner with ML scientists on the Enchant team to convert data needs into scalable acquisition and processing systems.

• Oversee and sustain distributed data pipelines in a production environment, troubleshoot failures, and enhance system resilience.

• Record data provenance, processing choices, and quality metrics to ensure reproducibility and facilitate auditing.

• Safely operate agents utilizing sandboxed execution, least-privilege credentials, restricted network access, and audit logs.

• Identify and communicate potential security vulnerabilities to the team.

• Contribute to the development of a long-term natural-language orchestrator for drug discovery inference, fine-tuning, virtual screenings, and dataset evaluation.

⛳️ Requirements

• Master’s degree in a computational STEM discipline, or a Bachelor’s degree with 2+ years of relevant industry experience.

• Proficient Python programming skills and a background in developing and supporting production-level software.

• Practical experience with LLM APIs such as Claude and GPT.

• Familiarity with agentic methodologies, encompassing tool utilization, orchestration, and multi-step reasoning.

• Understanding of biomedical or chemical data sources and formats, including PDB, UniProt, ChEMBL, SDF/MOL, and FASTA.

• Foundational knowledge of data engineering, including ETL design, data validation, and management of structured and unstructured data at scale.

• Experience with Python testing frameworks, particularly pytest fixtures and parameterization.

• Knowledge of agent orchestration frameworks and evaluation systems for LLM-generated code.

• Familiarity with cloud infrastructure and workflow orchestration tools such as AWS, Docker, and Kubernetes.

• Understanding of multimodal biomedical data, including small molecules, proteins, assays, images, ‘omics, and/or clinical records.

• Experience in constructing or curating large-scale datasets for ML model training.

• Awareness of agent security practices, including sandboxing, scoped credentials, and prompt injection techniques.

• Authorized to work in the United States; visa sponsorship details should be included in the application.

🏝️ Benefits

• Company-sponsored healthcare.

• Flexible spending accounts.

• Optional life insurance.

• 401K matching.

• Unlimited vacation policy.

• Onsite gym facilities.

• Dining options available.

• New state-of-the-art facility.

• Convenient access to excellent living and recreational areas.