Sachiv Chandramohan
AI Engineer · India · Remote
I'm Sachiv Chandramohan, an AI engineer working across medical AI and accelerated compute — from HeAR acoustic screening (0.8245 AUC) and multimodal TB systems to CUDA kernels and on-device inference. Previously founding engineer at Mednoia; I also freelance on production RAG and agent systems.
Medical AI → accelerated compute. Previously founding engineer @ Mednoia. ▊
Work
view all →- Founding Engineer @ MednoiaJun 2026 — Sep 2026
- AI Engineer (Freelance) @ ISSG & SpineDAOSep 2025 — Dec 2025
- Research Intern, Medical Imaging @ Breast Cancer Prediction (DCE-MRI)Jul 2025 — Sep 2025
Projects
view all →- BigTB6 — multimodal TB screening2026
Multimodal architecture fusing self-supervised HeAR acoustic embeddings with MedGemma + MedSigLIP vision-language models, with domain-aware expert routing for natural vs. forced coughs. 0.75 patient-level AUC, 5-fold CV across 33K samples. 2nd place, Agentic Track — MedGemma Impact Challenge ($5,000, 850+ teams).
- ORCA-G4 — on-device oral cancer screening2025
YOLO11 lesion-detection pipeline (273 images → 362 crops, up to 0.553 mAP@50), then Gemma fine-tuned with LoRA + 4-bit quantization on a single RTX 3090 for offline vision-language classification with JAX-exported on-device deployment.
- IndicPHI-Bench — multilingual eval framework2025
Reproducible evaluation framework spanning 23 Indian languages and 13 scripts; fine-tuned a 237M-parameter MuRIL encoder for 50 entity types to study multilingual transfer and character-level leakage.