Edge Platform Lead

Job Description Edge Platform Lead

Job Title: Edge Platform Lead
Location: Mumbai (Preferred)
Experience: 10- 15+ Years
Department: Engineering / Platform Engineering

Role Summary

The Edge Platform Lead will own the qualification, architecture, optimization, and lifecycle management of edge computing platforms used across industrial vision, AI inspection, serialization, and automation products. This role bridges hardware, operating systems, GPU acceleration, AI inference, networking, and application software to ensure reliable, scalable, and high-performance edge deployments.

The ideal candidate has extensive experience with industrial PCs, GPU platforms, embedded systems, Windows/Linux environments, AI inference optimization, and client-server architectures.

Key Responsibilities

Edge Platform Ownership

• Define and qualify hardware platforms for multiple product families and customer use cases.
• Evaluate CPUs, GPUs, NPUs, memory, storage, networking, and I/O performance.
• Standardize edge hardware platforms across products.
• Build long-term platform roadmap considering performance, lifecycle, availability, and cost.

Hardware Qualification

• Evaluate and benchmark:
• Industrial PCs
• Embedded edge devices
• GPU-based platforms
• AI accelerators
• Vision processing hardware
• Perform thermal, stress, endurance, reliability, and environmental testing.
• Establish qualification criteria and acceptance standards.

GPU & AI Processing

• Possess strong understanding of GPU computing architecture.
• Optimize applications using:
• CUDA
• TensorRT
• OpenCL (preferred)
• NVIDIA DeepStream (preferred)
• Benchmark AI inference performance.
• Optimize GPU utilization, latency, throughput, and power consumption.
• Evaluate different AI hardware platforms for varying workloads.

Operating Systems

• Expert understanding of:
• Windows
• Linux
• Configure operating systems for:
• High-performance vision systems
• Real-time applications
• Industrial deployments
• Optimize:
• Drivers
• Services
• Security
• Boot performance
• Resource utilization

Client-Server & Edge Architecture

• Design and validate deployment architecture involving:
• Edge devices
• Client applications
• Central servers
• Cloud connectivity
• Optimize communication performance.
• Ensure scalability and high availability.
• Support containerized deployments where applicable.

Camera & Vision Platform

• Strong understanding of industrial camera hardware:
• GigE Vision
• USB3 Vision
• CoaXPress
• Camera Link (preferred)
• Knowledge of:
• Sensor architecture
• ISP pipelines
• Image acquisition
• Frame grabbers
• Hardware triggering
• Synchronization
• Optimize camera performance with GPU-based processing pipelines.

AI Inference Platform

• Evaluate AI inference performance across multiple hardware platforms.
• Benchmark:
• Detection latency
• Throughput
• GPU utilization
• CPU utilization
• Memory consumption
• Optimize deployment of deep learning models for production environments.

Platform Validation

• Define validation methodology for:
• Edge hardware
• Client systems
• Servers
• GPU platforms
• Develop benchmark suites.
• Build qualification reports.
• Recommend platform improvements.

Cross-functional Collaboration

• Work closely with:
• AI Team
• Image Processing Team
• Software Engineering
• QA
• Product Management
• Hardware Vendors
• Drive technical decisions for platform selection.

Required Technical Skills

Hardware

• Industrial PCs
• Embedded Computing
• NVIDIA Jetson (preferred)
• Intel IPC platforms
• AMD & NVIDIA GPU platforms
• Storage architecture
• PCIe
• USB
• Ethernet
• Serial communication

GPU & AI

• CUDA
• TensorRT
• cuDNN
• OpenCL
• GPU profiling tools
• AI inference optimization
• Deep learning deployment

Operating Systems

• Windows
• Linux
• Kernel-level understanding (preferred)
• Driver installation and optimization
• System performance tuning

Networking

• TCP/IP
• Client-Server Architecture
• REST APIs
• OPC UA (preferred)
• MQTT (preferred)

Vision Systems

• Industrial cameras
• Image acquisition
• Camera SDK integration
• Hardware triggering
• Synchronization
• Image processing pipelines

Benchmarking & Validation

• Performance profiling
• Stress testing
• Thermal testing
• Reliability testing
• System diagnostics
• Hardware qualification methodologies

Preferred Skills

• NVIDIA DeepStream
• Docker / Containers
• Kubernetes (basic understanding)
• Edge AI deployment
• ONNX Runtime
• OpenVINO
• Embedded Linux
• Real-time operating systems (RTOS)
• Industrial automation
• PLC communication
• High-speed vision systems

Education

• Bachelors or Master’s degree in:
• Computer Engineering
• Electronics Engineering
• Electrical Engineering
• Embedded Systems
• Computer Science
• Mechatronics

Experience

• 10–15+ years in embedded, industrial, or edge computing.
• At least 5 years working with GPU-accelerated platforms.
• Experience qualifying hardware for production deployments.
• Hands-on experience with AI inference platforms.
• Experience supporting Windows and Linux-based industrial systems.
• Exposure to industrial vision or machine vision products is highly desirable.