Quality Control Analyst – Clinical Team

Quality Control Analyst – Clinical Team

About Triomics:

Triomics helps oncology organizations scale clinical research and high-quality data creation without scaling headcount. Our AI platform - powered by OncoLLM™ - automates the operational work behind trial screening, eligibility interpretation, and oncology data abstraction across Prism (trial matching), Harmony (registry + RWE curation), and Symphony (clinician copilot). Built for real-world hospital workflows, Triomics integrates with EHRs and CTMS systems and is deployed with leading academic cancer centers to improve speed, consistency, and audit-ready clinical accuracy.

Job Description:

Part of the Oncology Clinical Team, this role serves as the primary quality control checkpoint for all Medical Data Abstractors (MDAs) and Senior Medical Data Abstractors (Sr. MDAs). At Triomics, abstractors work within AI-assisted workflows — reviewing, validating, and refining AI-extracted diagnostic, pathology, imaging, and treatment data for accuracy and protocol compliance.

The QC Analyst audits this human-reviewed AI output to ensure the highest standard of clinical accuracy before data is finalized. This role may also contribute directly to AI-output review activities based on project requirements and will be rotated across projects in alignment with business needs.

Position Summary:

The Quality Control Analyst operates as the final review layer in Triomics' AI-assisted clinical data pipeline. Abstractors at Triomics evaluate, correct, and validate AI-extracted oncology data across diagnostic, pathology, imaging, and treatment domains. The QC Analyst audits the quality of this abstractor-reviewed output, ensuring that human corrections to AI extractions are accurate, consistent, and protocol-aligned.

This role is expected to maintain deep familiarity with AI-assisted abstraction workflows and contribute directly to review activities when project scope demands it.

Key Responsibilities:

• Perform structured QC reviews of abstractor-validated AI-extracted oncology data, auditing the accuracy and completeness of human corrections and annotations made by MDAs and Sr. MDAs.
• Validate that abstractor-reviewed outputs — spanning AI-extracted diagnostic findings, pathology results, imaging interpretations, and treatment records — meet protocol compliance and data quality standards.
• Identify and document systematic discrepancies between AI-extracted data and abstractor corrections, distinguishing model-level error patterns from human review errors.
• Provide structured, actionable feedback to MDAs and Sr. MDAs to improve the quality and consistency of their AI-output review and refinement decisions.
• Contribute directly to the review and refinement of AI-extracted clinical data on assigned projects, stepping into abstractor workflows as required by project scope or business need.
• Transition across projects as directed by project leads or operations, maintaining consistent QC standards across varied oncology study types and therapeutic areas.
• Conduct second-level reviews and contribute to benchmarking exercises that assess both abstractor performance and AI extraction accuracy.
• Collaborate with NLP, product, and operations teams to surface quality issues that have implications for AI model optimization or workflow design.
• Support calibration sessions and contribute to the development of SOPs and QC frameworks specific to AI-assisted abstraction environments.
• Maintain QC logs, quality metrics, and performance documentation across the Clinical Team.

Qualifications:

• Minimum 3 years of experience in oncology clinical data abstraction, clinical research, or related patient-treatment data analysis roles.
• Prior experience functioning in a Quality Analyst, QC Reviewer, or Quality Auditor capacity — either in the current or a previous role — is strongly preferred.
• Strong oncology domain expertise across diagnosis, staging, grading, and systemic therapies.
• Experience reviewing medical records and validating AI-assisted or structured data outputs against protocol-defined criteria.
• Comfort working within AI-assisted workflows and structured clinical data environments is essential — this role requires fluency in evaluating human corrections made to AI-generated extractions, not traditional manual abstraction review.
• Certification in Clinical Research or Clinical Data Management preferred.

Education:

B.Sc (Nursing), BDS, BAMS, BHMS, MDS, BPharm, MPharm

Skills and Abilities:

• Excellent written and verbal communication skills; able to deliver structured feedback and collaborate effectively with cross-functional and cross-level stakeholders in a fast-paced environment.
• High attention to detail with sound clinical judgment; able to distinguish AI extraction errors from abstractor review errors, and recommend appropriate corrective actions for each.
• Comfortable working independently while knowing when to escalate or seek senior input.
• Strong adaptability to shifting project assignments, evolving QC frameworks, and varied AI-assisted abstraction tools or databases.
• Proficient with Microsoft Office (Word, Excel, Outlook, PowerPoint); able to maintain QC logs, generate quality reports, and share professional documentation across teams.

Why Join Us?

1. We are revolutionizing a unique industry that has the potential to impact and benefit patients from all over the world - you can create impact at scale.
2. We have had company-sponsored workations in Bali, Sri Lanka, and Manali and take pride in our hard-working yet super fun culture.
3. We are working on a few of the most challenging problems in a highly regulated industry which provides you an opportunity to solve some of the most interesting things.
4. You will get a chance to work with experts from multiple industries and the best in the industry.

This role demands strong expertise in:

• Histological classification of solid malignancies — mainly breast, lung, GI, GU, and gynecological cancers.
• Hematologic cancers (leukemia, lymphoma, myeloma) — types, staging, diagnosis, and treatment.
• Biomarkers and tumor markers.
• TNM classification.
• Types of cancer therapy in detail.
• Line of therapy
• Mechanism of action of chemotherapy.