AI Infrastructure Engineer - Self-Hosted LLM & GPU Mastery

360-365 Marketing OPC; Taguig; On-site; PHP 1,674,000 - 2,790,000; Full time

Job summary

360-365 Marketing OPC is seeking a highly technical AI Engineer / MLOps Specialist to lead a core infrastructure migration toward a fully self-hosted, open-source AI architecture on AWS. You will own end-to-end pipelines, including data ingestion, vector database management, and secure LLM serving 24/7.

You should excel at allocating GPU VRAM, optimizing inference speeds, and managing bare-metal Linux servers, with a focus on cost efficiency and data privacy.

Qualifications

• AI / MLOps: Proven experience downloading raw model weights (Hugging Face) and serving locally on GPUs.
• Cloud Infrastructure: Hands-on AWS experience, spinning up, configuring, and securing persistent Linux EC2 VMs.
• Data Engineering / Python: Strong Python skills; proficient with modern web scraping libraries and handling messy HTML data.
• RAG Architecture: Deep understanding of embedding models, semantic chunking, and vector databases.
• DevOps: Highly proficient in Docker, NVIDIA Container Toolkit for GPU-accelerated apps. Bonus points for bringing SLM migration, advanced RAG, and reverse-proxy tooling.

Responsibilities

• Infrastructure Migration: Move from managed APIs to self-hosted open-source models (e.g., Llama 3, Qwen) on AWS EC2 GPUs.
• Data Ingestion & Scraping: Build Python pipelines/scrapers to daily fetch unstructured data from external sources.
• Vector Database Management: Embed text into a vector DB with upsert logic to avoid duplicates.
• Local LLM Serving: Deploy models with optimized engines; apply quantization (GGUF/AWQ) to prevent OOM.
• Backend Integration: Expose RAG via a secure, high-concurrency REST API (FastAPI).
• Cloud Security: Implement VPC routing, IAM roles, Security Groups for AWS EC2.

Skills

AI / MLOps

Cloud infrastructure

Python

RAG architecture

DevOps

Docker

NVIDIA Container Toolkit

Tools

Playwright

BeautifulSoup

Scrapy

Job description

360-365 Marketing OPC is seeking a highly technical AI Engineer / MLOps Specialist to lead a core infrastructure migration toward a fully self-hosted, open-source AI architecture on AWS. You will own end-to-end pipelines, including data ingestion, vector database management, and secure LLM serving 24/7.

You should excel at allocating GPU VRAM, optimizing inference speeds, and managing bare-metal Linux servers, with a focus on cost efficiency and data privacy.