Ron Jailall - Resume

Professional Profile

Senior Systems & AI Engineer with 15+ years of experience building robust, production-ready systems at scale. Expert in Swift, C++, and On-Device Inference, with a specific focus on VisionOS/AR and high-performance embedded systems. Proven track record of bridging the gap between research (AI/ML) and engineering (System Frameworks) to ship cutting-edge vision experiences under strict performance and privacy constraints.

Core Competencies

Languages: Swift, C++, Python, C#, Objective-C (Familiarity), Metal Shading Language (MSL).

Apple Ecosystem: VisionOS, RealityKit, CoreML, ARKit, Metal, AVFoundation.

AI & Computer Vision: On-Device Inference (LLMs/VLMs), Gaussian Splatting, TensorRT, Sensor Fusion (Camera/IMU).

Systems Engineering: Privacy-by-Design, Real-time Resource Management, Cross-Device Architecture, Performance Optimization.

Featured Systems Projects

Interactive Volumetric Rendering on VisionOS

Swift / RealityKit / Metal

System-Level Implementation: Engineered a native VisionOS application using Swift and RealityKit to render volumetric Gaussian Splats, overcoming strict browser-based memory sandboxing by moving to a native systems architecture.
Performance Optimization: Wrote custom Metal vertex and fragment shaders to implement real-time physics ("jiggle" effects) at high frame rates, optimizing GPU resource usage for the Apple Vision Pro hardware constraints.
On-Device AI Integration: Managed the end-to-end pipeline of converting research-grade models (SHARP) into optimized CoreML packages, ensuring efficient on-device inference without cloud dependency.

Real-Time Multi-View Tracking System

C++ / CUDA / Jetson

Sensor Data Processing: Architected a multi-camera tracking system on Nvidia Jetson embedded devices, writing optimized C++ and CUDA code to ingest and synchronize raw sensor streams in real-time.
Resource-Constrained Optimization: Optimized computer vision models using TensorRT and ONNX, achieving sub-millisecond latency on resource-constrained edge hardware.
Robustness: Implemented fault-tolerant GStreamer pipelines to ensure system stability and recovery during continuous operation in the field.

Professional Experience

ML Engineering Consultant / Systems Architect

2024 – Present

Remote

Building privacy-centric AI tools and high-performance vision systems.

Privacy & Security (FastRecord Project): Developed "FastRecord," a lightweight screen recording tool designed with privacy-by-design principles. Engineered the system to process all video data locally on-device, ensuring zero data egress to the cloud.
On-Device Inference & LLMs: Authored technical research on Apple's On-Device VLM, analyzing memory management strategies for running multimodal models locally. Architected "Matte Model," a CPU-optimized portrait matting system (MobileNetV2) deployed via Electron/ONNX, replacing heavy cloud dependencies with efficient local execution.
Cross-Functional Collaboration: Partnered with client engineering and product teams to translate high-level AI research goals into shipping technical requirements and production-ready code.

Lead Engineer, AI R&D

2023 – 2024

Vidable.ai | Remote

Bridging research and production engineering for GenAI products.

Systems-Level Thinking: Designed the infrastructure for deploying LLM inference on varied hardware targets, evaluating trade-offs between latency, cost, and model quality.
Research to Engineering: Collaborated closely with PhD researchers to validate "state-of-the-art" algorithms (Diffusion/Transformers) and refactor them into robust, maintainable production microservices.
Mentorship: Mentored junior engineers on shipping discipline, code quality, and the intricacies of deploying ML models to production environments.

Lead Engineer

2014 – 2023

Sonic Foundry | Remote

Engineering leadership for a video platform serving millions of users.

Shipping at Scale: Architected and maintained core data pipelines for a video platform used by the company's largest enterprise customers (100k+ concurrent users), ensuring high availability and system resilience.
Production Quality: Led the transition to cloud-native architectures (AWS Lambda/Batch), enforcing strict CI/CD practices (GitLab/Terraform) and code review standards across the team.
Team Leadership: Founded and led the internal AI reading group, fostering a culture of continuous learning and technical excellence across the engineering organization.