Remote Biomedical Informatics SME - 58854

Turing • Los Angeles, CA

Associate Posted April 2, 2026 Job link

Responsibilities

On the bioinformatics evaluation team at Turing, you'll design and develop rigorous, self-contained coding questions and automated, unit-test–backed evaluations that translate theoretical bioinformatics concepts into deterministic, performance-constrained problems with clear rubrics. You will cover advanced domains including nonlinear and longitudinal modeling, EHR and clinical data science, a wide range of drug discovery and chemoinformatics topics, molecular dynamics and structural analysis, as well as software tooling, workflow automation, and reproducibility in bioinformatics. You’ll also incorporate regulatory science, clinical guidelines, ethical and safety considerations, and clinical validation into scenario-based questions to comprehensively assess AI model capabilities.

Commitments

You will work fully remotely as a contractor for about two months, committing 30–40 hours per week on a freelance basis without medical or paid leave, with potential for contract extension. The role involves contributing to cutting-edge AI projects with leading LLM companies and requires completing a 2–6 hour take-home assessment in biomedical informatics followed by a short delivery discussion. After applying, you’ll access Turing’s portal via a login link to complete your profile, and you may also participate in their referral program.

Responsibilities

Design and develop challenging bioinformatics coding questions that push the limits of AI model capabilities.
Create automated, coding-based evaluations with unit tests that objectively verify correctness.
Build comprehensive evaluation rubrics with 7–10 distinct criteria for each bioinformatics question.
Ensure every question is self-contained, well-defined, and completely unambiguous, including all domain rules and edge cases.
Develop problems where there is exactly one correct answer or outcome that can be deterministically validated.
Translate theoretical bioinformatics concepts into concrete, measurable outputs.
Enforce performance requirements with explicit constraints and tests to prevent inefficient or brute-force solutions.
Nonlinear, Statistical, and Adaptive Signal Analysis
Longitudinal Patient Modeling and Disease Progression
Electronic Health Records and Clinical Data Science 4.
Drug Discovery & Repurposing
Treatment response prediction
Structure-based drug design (Molecular docking, binding site analysis, Virtual screening workflow)
Protein structure analysis (PDB/mmCIF handling)
Chemoinformatics ( Ligand-based screening, molecular fingerprinting, 2D/3D data handling and chemical space analysis)
QSAR & ADMET Modeling
Drug–target interaction prediction
Drug sensitivity prediction in disease models
Repurposing via omics/network associations
Predictive Modeling for Drug Discovery Molecular Dynamics Simulation of Biomolecules (QM, DFT, stability, reactivity, PCA analysis ) 5.
Software / Utilities
Tool installation & environment management (docker/conda/pip)
Format conversion/validation (FASTA/FASTQ, BAM/VCF, PDB)
GUI-driven analysis workflows (step-by-step runs)
Workflow automation (scripts wrapping GUI tools)
Visualization tools (genome browsers, 3D viewers)
Container/VM execution and troubleshooting
Batch processing and report generation
Pipeline interoperability checks
Reproducibility packaging (configs, manifests)
Debugging typical bioinformatics tool errors 6.
Regulatory Science and Clinical Policies
FDA/EMA regulatory pathways
Clinical Practice Guidelines & Standards of Care (e.g., NCCN, AHA, etc.)
Diagnostic Biomarker & Therapeutic Use Constraints
Medical Scenario Reasoning (case vignettes, Differential diagnosis)
Data & Content Compliance
Ethical Use, Safety, and Harm Prevention
Model Use Governance & Auditability
Policy‑Aligned Language & Communication
Clinical validation and cohort generalization

Not Met Priorities

What still needs stronger evidence

Requirements

Preferred Skills

Image sampling theory and resolution limits
Geometric transformations and spatial calibration
Nonlinear, Statistical, and Adaptive Signal Analysis
Policy‑Aligned Language & Communication
Clinical validation and cohort generalization
Privacy‑preserving learning Perks of Freelancing With Turing:

Education

(Required) – Required Qualifications: Educational Background
(Not required) – Master's degree of experience in biomedical data processing and interpretation.
(Not required) – Ongoing PhD with 3+ years of experience in biomedical data processing and interpretation.
(Not required) – PhD (completed) in Biomedical Informatics, Bioinformatics, Computational Biology or a closely related field (preferred).

About Turing: Based in San Francisco, California, Turing is the world’s leading research accelerator for frontier AI labs and a trusted partner for global enterprises deploying advanced AI systems. Turing supports customers in two ways: first, by accelerating frontier research with high-quality data, advanced training pipelines, plus top AI researchers who specialize in coding, reasoning, STEM, multilinguality, multimodality, and agents; and second, by applying that expertise to help enterprises transform AI from proof of concept into proprietary intelligence with systems that perform reliably, deliver measurable impact, and drive lasting results on the P&L Role Overview: We are seeking highly skilled Biomedical Informatics Subject Matter Experts (SMEs) to join our team in developing rigorous, high-quality evaluation questions designed to assess and challenge advanced AI models. The primary objective is to create benchmark questions that test the boundaries of AI capabilities across diverse bioinformatics domains. This role requires deep technical expertise combined with the ability to craft precise, unambiguous questions with well-defined evaluations. The ideal candidate will possess not only strong theoretical knowledge but also practical experience in designing assessment materials that have deterministic, verifiable outcomes. Responsibilities:
Design and develop challenging bioinformatics coding questions that push the limits of AI model capabilities.
Create automated, coding-based evaluations with unit tests that objectively verify correctness.
Build comprehensive evaluation rubrics with 7–10 distinct criteria for each bioinformatics question.
Ensure every question is self-contained, well-defined, and completely unambiguous, including all domain rules and edge cases.
Develop problems where there is exactly one correct answer or outcome that can be deterministically validated.
Translate theoretical bioinformatics concepts into concrete, measurable outputs.
Enforce performance requirements with explicit constraints and tests to prevent inefficient or brute-force solutions. Required Qualifications: Educational Background
Master's degree of experience in biomedical data processing and interpretation.
Ongoing PhD with 3+ years of experience in biomedical data processing and interpretation.
PhD (completed) in Biomedical Informatics, Bioinformatics, Computational Biology or a closely related field (preferred). Technical and other skills
Strong proficiency in biomedical data processing, analysis, and interpretation , including working with large‑scale datasets.
Experience with bioinformatics tools and pipelines (e.g., NGS workflows, multi‑omics, etc.).
Solid programming skills in Python / R
Experience working in Linux/Unix , Docker and version control.
Strong communication and collaboration skills for working in interdisciplinary research teams Domain Expertise Requirements Candidates must demonstrate deep, expert-level knowledge in at least TWO (2) of the following five core bioinformatics domains: 1. Biomedical Image Processing
Processing of Radiology imaging: CT, MRI, PET/SPECT, Ultrasound imaging
Automating cell counting, identifying cell types, and analyzing tissue structures in pathology slides
Computational segmentation and boundary inference
Medical image formation, reconstruction & enhancement
Noise modeling and statistical denoising
Image sampling theory and resolution limits
Intensity standardization and harmonization
Geometric transformations and spatial calibration
Multi-modal image registration and alignment
Morphological and topological shape analysis
Quantitative imaging feature extraction
Fusing data from different modalities (MRI, PET, Genomics) for a comprehensive view to tailor treatments
pattern recognition and predictive modeling 2. Biomedical Signal Processing
Cardiovascular/hemodynamic signals (ECG, PPG, BP, HRV, etc)
Neural/brain electrical signals (EEG, EP/ERP; seizure/cognitive analysis)
Neuromuscular/motor signals (EMG, motor unit decomposition; prosthetics/rehab)
Ocular/visual system signals (EOG, blink/saccade analysis)
Respiratory signals (airflow, effort; sleep/disordered breathing)
Nonlinear, Statistical, and Adaptive Signal Analysis
Multichannel, Spatial, and Connectivity Signal Analysis
Machine Learning and Data‑Driven Biomedical Signal Analysis
Clinical Monitoring, Wearable, and Translational Signal Processing 3. Molecular & Omics based Personalized Medicine
Omics based risk / disease prediction (GWAS, PRS, bulk, single‑cell RNA‑seq, proteins / metabolite signatures associated with diseases)
Risk Prediction and Prognosis Modeling
Molecular patient subtyping
Liquid Biopsy and Circulating Biomarkers (ctDNA, cfRNA/miRNA, MRD, etc.)
Causal Inference & Mechanistic Inference (ATE/CATE, Trial emulation and counterfactual modeling)
Cross‑modal data fusion (omics + EHR + imaging / signals)
Longitudinal Patient Modeling and Disease Progression
Patient Stratification and Subtyping (molecular subtypes, endotypes)
Electronic Health Records and Clinical Data Science 4. Drug Discovery & Repurposing
Treatment response prediction
Structure-based drug design (Molecular docking, binding site analysis, Virtual screening workflow)
Protein structure analysis (PDB/mmCIF handling)
Chemoinformatics ( Ligand-based screening, molecular fingerprinting, 2D/3D data handling and chemical space analysis)
QSAR & ADMET Modeling
Drug–target interaction prediction
Drug sensitivity prediction in disease models
Repurposing via omics/network associations
Predictive Modeling for Drug Discovery Molecular Dynamics Simulation of Biomolecules (QM, DFT, stability, reactivity, PCA analysis ) 5. Software / Utilities
Tool installation & environment management (docker/conda/pip)
Format conversion/validation (FASTA/FASTQ, BAM/VCF, PDB)
GUI-driven analysis workflows (step-by-step runs)
Workflow automation (scripts wrapping GUI tools)
Visualization tools (genome browsers, 3D viewers)
Container/VM execution and troubleshooting
Batch processing and report generation
Pipeline interoperability checks
Reproducibility packaging (configs, manifests)
Debugging typical bioinformatics tool errors 6. Regulatory Science and Clinical Policies
FDA/EMA regulatory pathways
Clinical Practice Guidelines & Standards of Care (e.g., NCCN, AHA, etc.)
Diagnostic Biomarker & Therapeutic Use Constraints
Medical Scenario Reasoning (case vignettes, Differential diagnosis)
Data & Content Compliance
Ethical Use, Safety, and Harm Prevention
Model Use Governance & Auditability
Policy‑Aligned Language & Communication
Clinical validation and cohort generalization
Privacy‑preserving learning Perks of Freelancing With Turing:
Work in a fully remote environment.
Opportunity to work on cutting-edge AI projects with leading LLM companies.
Potential for contract extension based on performance and project needs. Offer Details:
Commitments Required : At least 30 hours per week. (We have 2 options of time commitment: 30 hrs/week or 40 hrs/week)
Engagement type : Contractor assignment/freelancer (no medical/paid leave)
Duration of contract : 2 months; [expected start date is next week] Evaluation Process:
Take home Assessment on Biomedical Informatics (2-6 hours)
Delivery discussion(15-30mins) After applying, you will receive an email with a login link. Please use that link to access the portal and complete your profile. Know amazing talent? Refer them at turing.com/referrals, and earn money from your network.