Biomedical Informatics SME – AI Model Evaluation

𝗔𝗯𝗼𝘂𝘁 𝗗𝗲𝘀𝘁𝗶𝗻𝗮𝗿𝗲 𝗦𝗲𝗿𝘃𝗶𝗰𝗲𝘀

Destinare Services is a global IT recruitment firm connecting top technology companies with skilled engineering talent across AI, machine learning, data, and backend engineering. We specialize in remote-first roles and support innovative, research-driven teams worldwide.

Work with top global technology companies — from anywhere.

Visit www.destinareservices.com for more details.

𝗥𝗼𝗹𝗲 𝗢𝘃𝗲𝗿𝘃𝗶𝗲𝘄

We are seeking highly skilled Biomedical Informatics Subject Matter Experts (SMEs) to collaborate with AI researchers on the development of rigorous, high-quality evaluation benchmarks for advanced AI and Large Language Models (LLMs).

The primary objective of this role is to design deterministic, verifiable benchmark questions that test the limits of AI capabilities across complex biomedical and bioinformatics domains. This position requires deep domain expertise, strong analytical thinking, and the ability to craft precise, unambiguous evaluation problems with clearly defined outcomes.

No prior AI experience is required.

𝗪𝗵𝗮𝘁 𝗗𝗼𝗲𝘀 𝗗𝗮𝘆-𝘁𝗼-𝗗𝗮𝘆 𝗟𝗼𝗼𝗸 𝗟𝗶𝗸𝗲

• Design and develop challenging bioinformatics coding problems that push AI model reasoning and execution limits

• Create automated, code-based evaluations with unit tests to objectively verify correctness

• Build detailed evaluation rubrics with 7–10 clearly defined criteria per question

• Ensure all questions are self-contained, deterministic, and unambiguous, covering rules, assumptions, and edge cases

• Develop problems with exactly one correct, verifiable outcome

• Translate theoretical biomedical concepts into concrete, testable outputs

• Define explicit performance constraints to prevent brute-force or inefficient solutions

• Collaborate with AI researchers and fellow SMEs to shape training strategies, evaluation methods, and benchmarks

𝗥𝗲𝗾𝘂𝗶𝗿𝗲𝗱 𝗤𝘂𝗮𝗹𝗶𝗳𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀𝗘𝗱𝘂𝗰𝗮𝘁𝗶𝗼𝗻𝗮𝗹 𝗕𝗮𝗰𝗸𝗴𝗿𝗼𝘂𝗻𝗱

• Master’s degree with hands-on experience in biomedical data processing and interpretation

• OR ongoing PhD with 3+ years of relevant experience

• OR completed PhD in Biomedical Informatics, Bioinformatics, Computational Biology, or a closely related field (preferred)

𝗗𝗼𝗺𝗮𝗶𝗻 𝗘𝘅𝗽𝗲𝗿𝘁𝗶𝘀𝗲 𝗥𝗲𝗾𝘂𝗶𝗿𝗲𝗺𝗲𝗻𝘁

Candidates must demonstrate expert-level proficiency in at least TWO (2) of the following domains:

1. Biomedical Image Processing

• CT, MRI, PET/SPECT, Ultrasound imaging

• Pathology image analysis (cell counting, tissue structure analysis)

• Image segmentation, boundary inference, reconstruction, enhancement

• Noise modeling, denoising, sampling theory, resolution limits

• Image registration, multimodal alignment, spatial calibration

• Quantitative imaging feature extraction and predictive modeling

• Multimodal fusion (imaging, genomics, signals)

2. Biomedical Signal Processing

• ECG, PPG, BP, HRV, EEG, EMG, EOG, respiratory signals

• Nonlinear, statistical, and adaptive signal analysis

• Multichannel, spatial, and connectivity analysis

• Machine learning–driven signal interpretation

• Wearable, clinical, and translational monitoring systems

3. Molecular & Omics-Based Personalized Medicine

• GWAS, PRS, bulk and single-cell RNA-seq, proteomics, metabolomics

• Risk prediction, prognosis modeling, patient stratification

• Liquid biopsy and circulating biomarkers

• Causal inference, trial emulation, longitudinal modeling

• Cross-modal data fusion (omics + EHR + imaging/signals)

4. Drug Discovery & Repurposing

• Structure-based drug design and virtual screening

• Protein structure analysis (PDB/mmCIF)

• Chemoinformatics, QSAR, ADMET modeling

• Drug–target interaction and sensitivity prediction

• Molecular dynamics simulation and stability analysis

5. Regulatory Science & Clinical Policy

• FDA/EMA pathways and clinical practice guidelines

• Diagnostic and therapeutic validation constraints

• Ethical AI use, safety, compliance, and governance

• Privacy-preserving learning and auditability

𝗪𝗵𝘆 𝗝𝗼𝗶𝗻 𝗨𝘀

• Apply deep biomedical expertise to cutting-edge AI systems shaping the future of healthcare

• Influence how next-generation AI models reason about complex biomedical problems

• Collaborate with global AI researchers and domain experts

• Fully remote, intellectually challenging work with real-world impact

• Contribute without needing prior AI or machine learning experience

𝗢𝘁𝗵𝗲𝗿 𝗗𝗲𝘁𝗮𝗶𝗹𝘀

• Fully remote role

• Contractor assignment

• Contract duration: 3–6 months (expected start: next week)

• Work commitment: 8 hours/day with 4-hour PST overlap

𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 𝗣𝗿𝗼𝗰𝗲𝘀𝘀

• Round 1: MCQs and take-home assessment

• Round 2: Delivery interview