Professional Journey

Machine Learning Engineer — RSK IT InternationalSept 2025 – Present · Remote
  • Engineered low-latency streaming audio pipelines for drive-thru, toll-booth, and parking-lot voice agents across 3 live sites — 80–120 ms chunking, VAD/directed-speech gating, ASR, and intent routing into POS, tolling, and gate-control systems, holding end-to-end turn times under ~500 ms in real traffic.
  • Architected and deployed serving topologies for 3 production customers and 2 active POCs across on-prem edge devices and hybrid edge/cloud, with containerized ASR/NLU microservices and gRPC/WebRTC streaming clients.
  • Built a RAG-based post-sales QA helper indexing ~75 internal runbooks and troubleshooting guides, plus a three-agent ticket-routing layer (documentation, infra, model) that cut misrouted tickets and cross-team handoffs.
AI/ML Research Assistant — Amal Lab, Northeastern UniversityJune 2024 – Aug 2025 · Boston
  • Trained a production deep-learning classifier to 97.28% accuracy on skin-cancer detection via comparative analysis of ResNet-34, EfficientNet-B1, and Vision Transformers with ensembles and external validation across 3 datasets.
  • Engineered a Med-SAM medical image segmentation system for MRI, CT, and histopathology data with automated preprocessing and fine-tuned transformer architectures.
  • Scaled infrastructure processing 18TB+ TCGA multi-omics data on Apache Spark and Dask for biomarker discovery across 33+ cancer types.
Research Data Scientist — Brigham and Women's HospitalAug 2024 – Dec 2024 · Boston
  • Developed a clinical-trial analytics pipeline over 10,000+ pharmaceutical reports using BERT and RoBERTa to link media sentiment with regulatory failure rates.
  • Designed a HIPAA-compliant meta-analysis framework across ClinicalTrials.gov and PubMed using random forests, gradient boosting, and statistical modeling (Cox proportional hazards, mixed-effects).