Senior Data Scientist JD - RP Labs -

Role Summary

We are seeking a Senior Data Scientist to lead production delivery of AI/ML and computer vision solutions for laboratory workflows that test and characterize rock and fluid samples. The role focuses on deploying robust, scalable models, improving speed, repeatability, and QA/QC consistency across lab sites.

Key Responsibilities

- Lead end-to-end delivery of production-grade computer vision and AI/ML solutions: problem framing, data strategy, model development, validation with lab SMEs, deployment, monitoring, and continuous improvement.
- Define data and labeling strategies suited to lab realities: limited ground truth, noisy labels, sample prep variability, instrument/site variation, and domain shift.
- Establish measurable acceptance criteria tied to lab operations (repeatability, bias/uncertainty, turnaround time improvements) and partner with QA/QC to embed these into release gates.
- Develop and maintain ML pipelines (training → evaluation → packaging → inference) with robust reproducibility: dataset/version control, experiment tracking, and model governance documentation.
- Collaborate with data engineering and software teams to integrate models into lab systems (APIs, batch pipelines, on-prem/edge execution where required) and ensure operational reliability.
- Own model lifecycle operations: monitoring, drift detection, alerting, root-cause analysis for performance changes, and retraining plans.
- Provide technical leadership: architecture decisions, design reviews, coaching/mentoring of junior data scientists/ML engineers.

Required Qualifications (Education & Experience)




- PhD + 10 years of relevant industry experience OR Master’s + 15 years of relevant industry experience in Data Science, Computer Vision, Machine Learning, Computer Science, Applied Mathematics/Physics, Geoscience/Petrophysics with computational specialization, or related fields.

Required Skills & Experience
- Demonstrated experience delivering computer vision + AI/ML solutions to production (not only research prototypes).
- Strong hands-on capability in:
- 2D computer vision (classification, detection, segmentation, anomaly detection).
- 3D/volumetric data (micro‑CT) processing and modeling.
- Model evaluation and error analysis using fit-for-purpose metrics (e.g., IoU/Dice, mAP, calibration, uncertainty estimation).

- Proficiency in Python and common ML/CV ecosystems (e.g., Num Py, Pandas, scikit-learn, PyTorch/Tensor Flow, OpenCV). Experience with 3D tooling is a plus (e.g., SimpleITK, scikit-image, VTK, MONAI).
- Strong data-centric ML practices: labeling strategy, dataset QA, handling class imbalance, active learning, and robust validation across sites/instruments.
- Experience with productionization and MLOps concepts: packaging, inference optimization, monitoring/drift, CI/CD for ML, experiment tracking, and model registry (tooling may vary).
- Ability to translate lab SME requirements into deployable technical specifications and communicate trade-offs clearly.

Preferred Qualifications
- Background in scientific imaging domains (materials science, geoscience/petrophysics, microscopy, CT).
- Experience with segmentation of porous media and 3D morphology features.
- Experience deploying in constrained environments (on-prem lab networks, edge workstations).
- Track record of setting up operational model governance (release gates, rollback plans, performance dashboards).

📌 Senior Data Scientist - RP Labs (India)
🏢 GK HR Consulting India Private
📍 India