About Me
Senior IoT & Edge AI Engineer
IoT and Edge AI engineer with 7+ years delivering end-to-end products across healthcare, wearables, and fitness-tech. Ships on-device ML (EfficientNet-B0, TFLite, ONNX Runtime, INT8 quantization) alongside full embedded firmware stacks (nRF52, ESP32, FreeRTOS, BLE/GATT). Led an 8-engineer cross-functional team delivering a regulatory-grade medical device platform. International experience across the US, UK, Belgium, and India.
- EfficientNet-B0 → ONNX INT8: 94.7% accuracy, <500ms on Pi Zero 2W
- TFLite on nRF52: 92% accuracy, <50ms inference on Cortex-M
- Dual-hardware IoT: Pi 5 / Pi Zero 2W + AES-256-GCM BLE + AWS IoT
- 40% faster releases via CI/CD · 500+ active patient sessions
Experience
Senior Engineer & Technical Lead
OraLens Healthcare · Bengaluru, India
- Led 8-engineer cross-functional team building a cloud-connected medical device platform; architecture passed regulatory review on first submission.
- Architected dual-hardware IoT system (ESP32 + Raspberry Pi 5 / Pi Zero 2W) with AES-256-GCM encrypted BLE, MQTT cloud sync to AWS IoT Core, and 72-hour SQLCipher offline buffer — 500+ active patient sessions in production.
- Trained and deployed EfficientNet-B0 (ONNX Runtime + DirectML) achieving 94.7% accuracy across 11 oral disease categories on 78,000 images; screening pipeline reduced clinician review time by 30%.
- Applied INT8 ONNX quantization for 2-3× inference speedup with <2% accuracy loss — Pi Zero 2W deployment at 1.5-2W, 10-20% CPU, <280MB RAM.
- Implemented CI/CD pipelines and automated test frameworks — 40% faster releases, 25% fewer post-release defects.
IoTHardwareML/AIAWSCI/CD
Jan 2022 – Jan 2025
- Designed full wearable firmware from scratch on nRF52 (BLE/GATT stack, sensor integration, power management, on-device DSP) — shipped to EU market across 30-50 care homes monitoring ~3,000 elderly residents.
- Deployed TFLite activity-recognition model via Edge Impulse: 92% accuracy, <50ms inference on Cortex-M MCU.
- Engineered adaptive sensor duty-cycling and dynamic sampling algorithms extending battery life by 40% (+2 days between charges).
- Built sensor-data pipeline (collection, labelling, pre-processing) reducing ML model iteration time from weeks to days.
- Stood up HIL + unit + integration test framework — 35% release quality improvement, QA cycles from 2 weeks to 3 days.
BLEFreeRTOSEdge MLFirmwareEU Market
IoT Systems Engineer – Fitness Technology
Renovatio Systems Ltd· United Kingdom
- Developed ESP32-based smart gym equipment firmware with real-time strain-gauge load measurement — ±0.5 kg accuracy across 0–200 kg range.
- Implemented MQTT-based cloud sync layer for live workout tracking, enabling real-time data delivery for 1,000+ users.
- Evaluated and benchmarked 4 sensor technologies (strain gauge, load cell, piezo, capacitive); recommended optimal solution balancing accuracy, cost, and power.
- Produced manufacturing-ready deliverables: circuit schematics, system architecture docs, and calibration procedures.
ESP32MQTTFirmwareSensor Integration
Project Engineer
Ralph L Wadsworth Construction· Draper, Utah, USA
- Led engineering execution on Denver Airport expansion, delivering 2 months ahead of schedule through data-driven sequencing and quality optimisation.
- Established QA inspection protocols and design-change workflows — zero safety non-conformances across the project lifecycle.
Project ManagementQAConstruction Engineering
Technical Skills
Embedded & Firmware
ESP32STM32Raspberry Pi 5/Zero 2WnRF52FreeRTOSPlatformIO
IoT & Protocols
BLE / GATTMQTTI2C / SPI / UARTAWS IoT CoreAES-256-GCMSQLCipher
ML & Edge AI
ONNX RuntimeDirectMLEfficientNet-B0INT8 QuantizationTensorFlow LiteEdge Impulse
Robotics & Control
ROSSLAMPID ControlPath PlanningMATLAB/SimulinkImpedance Control
Sensor Fusion & DSP
IMUStrain GaugeLoad CellKalman FilterReal-Time DSPSignal Processing
Full-Stack & Cloud
Go / GinReact / Next.jsFlutterPostgreSQLDockerAWS (EC2, S3, Lambda)
Education
M.S. Mechanical Engineering – Robotics & Control Systems
University of Utah
Salt Lake City, UT, USA · 2019
GPA 3.6 / 4.0B.Tech Mechatronics Engineering
S.R.M University
Chennai, India · 2012
GPA 8.8 / 10Certifications
Engineering × Product PhilosophyBuild the whole thing.
Build the whole thing.
Own the whole stack.
The best products are built by people who can move between the firmware and the feature spec — who understand why the BLE stack latency matters for the UX, and why the clinical workflow constraint changes the data model.