Edge AI Systems & Solutions Intern

Talons Laboratories Pte Ltd; Singapore; Vor Ort; SGD 20.000 - 27.000; Teilzeit

Zusammenfassung

Talons Laboratories Pte Ltd invites an Edge AI & Solution Integration Intern to join our core engineering team in Singapore. You will work at the intersection of high-VRAM hardware deployment, containerized AI models, OCR pipelines, and secure API frameworks on-premise.

You will help package, configure, and deploy robust in-a-box AI appliances, optimize system performance, and gain hands-on experience with edge AI infrastructure in a production-like environment.

Qualifikationen

• Pursuing a Bachelor’s or Master’s in a related technical field.
• Proficiency in Python or JavaScript/TypeScript.
• Experience with containerization and REST APIs.
• Interest in edge AI, OCR, and high-VRAM hardware.

Aufgaben

• High-VRAM On-Premise AI & Container Deployment: Deploy, configure, optimize, and manage containerized LLMs and AI pipelines locally.
• Solutions Development & Architecture: Design, build, and maintain scalable software solutions and backend services for high-throughput data processing.
• Hardware-Software Integration: Set up, configure, validate, and benchmark high-performance hardware systems and software stacks.
• OCR & Document Processing Pipelines: Implement, benchmark, and optimize OCR tools and document parsing on-premise.
• API Integration & Data Workflows: Build, secure RESTful APIs and SDKs for local data exchange.
• Testing, Troubleshooting & Performance Optimization: Conduct integration testing, profile memory usage, and troubleshoot bottlenecks.
• Technical Documentation & Handoff: Document architectures and deployment workflows for transfer to full-time teams.

Kenntnisse

Python

JavaScript/TypeScript

C/C++

GPU/AI concepts

Ausbildung

Bachelor’s/Master’s in CS/Engineering

Tools

Docker

Docker Compose

REST/JSON

Jobbeschreibung

About the Role

We are looking for an Edge AI & Solution Integration Intern to join our core engineering team. In this role, you will work at the intersection of high-performance local hardware deployment, advanced solutions architecture, and on-premise AI execution. You will help package, configure, and deploy robust "in-a-box" AI appliances—leveraging high-VRAM systems (16GB and above, such as high-end workstations and enterprise AI nodes)—to run localized containerized AI models, high-accuracy OCR pipelines, and secure API frameworks. This role offers hands‑on experience in cutting‑edge edge‑AI infrastructure, system optimization, and direct impact on high-performance local production capabilities.

Key Responsibilities

• High-VRAM On-Premise AI & Container Deployment: Deploy, configure, optimize, and manage containerized large language models (LLMs), multi-modal AI pipelines, and microservices locally onto high-performance hardware appliances and desktop workstations.
• Solutions Development & Architecture: Design, build, and maintain scalable software solutions and backend services to support high‑throughput data processing pipelines and local system modules.
• Hardware-Software Integration: Assist in the setup, configuration, validation, and benchmarking of high-performance "in-a-box" hardware systems, ensuring seamless synchronization between high-VRAM compute nodes and local software stacks.
• OCR & Document Processing Pipelines: Implement, benchmark, and optimize advanced Optical Character Recognition (OCR) tools and document‑parsing algorithms to process complex unstructured payloads entirely on-premise.
• API Integration & Data Workflows: Build, consume, and secure RESTful APIs and modern SDKs to facilitate reliable local data exchange between high‑performance hardware endpoints, containerized services, and user interfaces.
• Testing, Troubleshooting & Performance Optimization: Conduct rigorous integration testing, profile GPU memory and VRAM utilization, troubleshoot inference bottlenecks, and adhere to security best practices.
• Technical Documentation & Handoff: Document system architectures, local deployment protocols, and container optimization workflows to facilitate seamless knowledge transfer to full‑time engineering teams.

Key Qualifications

• Education: Currently pursuing a Bachelor’s or Master’s in Computer Science, Computer Engineering, Electrical Engineering, Software Engineering, Information Technology, or a related technical discipline.
• Technical Stack & Experience:
  • Languages & Frameworks: Proficiency in Python, JavaScript/TypeScript, or C/C++.
  • Core Concepts & Tools: Containerization (Docker, Docker Compose), modern APIs (REST/JSON), and hardware-software interfacing.
  • Domain Exposure: Academic or practical interest in high-VRAM local/edge AI model deployment, containerized microservices, Optical Character Recognition (OCR), or high-performance hardware workstations.
• Nice-to-Have (Bonus):
  • Prior hands‑on exposure to high-performance local AI hardware (e.g., CUDA-accelerated workstations, enterprise mobile/desktop AI nodes, or custom "in-a-box" hardware appliances).
  • Familiarity with GPU acceleration frameworks (CUDA, TensorRT, vLLM) and lightweight orchestration tools.
  • Basic understanding of data security, networking fundamentals, or version control (Git).