LLM Infrastructure Engineer - Cloud Infrastructure

Description :

About BeGig :

BeGig is the leading tech freelancing marketplace.

We empower innovative, early-stage, non-tech founders to bring their visions to life by connecting them with top-tier freelance talent.

By joining BeGig, youre not just taking on one roleyoure signing up for a platform that will continuously match you with high-impact opportunities tailored to your expertise.

Your Opportunity :

Join BeGig as an LLM Infrastructure Engineer and power the next wave of AI-driven applications.

Youll architect and scale infrastructure for large language models (LLMs), supporting inference, fine-tuning, and seamless integration in production systems.

Role Overview :

As an LLM Infrastructure Engineer, you will :

- Design, deploy, and optimize cloud infrastructure for training and serving LLMs at scale.

- Manage GPU/TPU clusters and containerized ML workloads (Kubernetes, Docker, Ray, etc.

- Implement monitoring, logging, and auto-scaling for high-availability AI systems.

- Collaborate with AI engineers, data scientists, and product teams to productionize LLM workflows.

- Ensure infrastructure security, compliance, and cost-effectiveness.

Technical Requirements & Skills :

- Experience : 3+ years in ML infrastructure, MLOps, or cloud engineering.

- Platforms : Deep experience with AWS, GCP, or Azure for ML workloads.

- Orchestration : Familiarity with Kubernetes, Docker, MLflow, Ray, or Airflow.

- LLMs : Understanding of LLM architectures (e.g, GPT, Gemini, Llama), deployment, and scaling challenges.

- Scripting : Strong Python or Bash skills for automation and pipeline management.

What Were Looking For :

An engineer passionate about building the backbone of modern AI systems.

Proactive in optimizing performance, reliability, and cost at every layer.

A strong collaborator who communicates clearly across AI, infra, and product teams.

Why Join Us? :

Impact : Build the infrastructure powering next-gen AI products and services.

Flexibility : Choose projects that match your expertisework fully remote.

Community : Be a key part of a fast-growing AI and engineering talent marketplace