LLM Infrastructure Engineer(Freelance | WFH)

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, you’re not just taking on one role—you’re signing up for a platform that will continuously match you with high-impact opportunities tailored to your expertise.

Your Opportunity

Join our network as an LLM Infrastructure Engineer and help architect, deploy, and scale robust infrastructure for large language models (LLMs) that power next-generation AI products. Your expertise will be critical in ensuring low-latency inference, seamless scaling, and secure operations of language models in production environments.

This role is fully remote, with flexible hourly or project-based engagements.

Role Overview

As an LLM Infrastructure Engineer, you will:

• Architect LLM Systems: Design and implement infrastructure for hosting, deploying, and scaling LLMs on cloud or on-premise environments.
• Optimize Inference: Set up high-throughput, low-latency serving using GPU/TPU clusters, inference engines, and load balancers.
• Model Versioning & Management: Implement model registries, versioning, and rollbacks to support experimentation and safe releases.
• Automate Deployments: Develop CI/CD pipelines and infrastructure-as-code for rapid and reliable deployment of LLM services.
• Monitor & Maintain: Set up observability (logging, monitoring, alerting) for LLM endpoints using tools like Prometheus, Grafana, or ELK stack.
• Ensure Security & Compliance: Apply best practices in access management, data privacy, and secure inference.

Technical Requirements & Skills

• Experience: Minimum 2+ years in infrastructure engineering, MLOps, or cloud operations—ideally with large-scale ML/AI systems.
• Cloud Platforms: Strong hands-on experience with AWS, GCP, or Azure for high-performance ML workloads.
• Model Serving: Proficiency with inference engines (Triton, TorchServe, Ray Serve, etc.) and deployment of LLMs at scale.
• Containerization & Orchestration: Experience with Docker, Kubernetes, and GPU scheduling for scalable serving.
• Automation: Experience building CI/CD pipelines and using infrastructure-as-code (Terraform, CloudFormation, etc.).
• Monitoring: Familiarity with monitoring, logging, and alerting tools for real-time production health.
• Security: Understanding of secure deployment, data protection, and compliance in ML environments.

What We’re Looking For

• An infrastructure engineer with a passion for enabling production-grade, performant AI at scale.
• A freelancer who can turn AI research models into reliable, customer-facing services.
• A systems thinker who anticipates bottlenecks and proactively optimizes for reliability and cost.

Why Join Us?

• Immediate Impact: Help startups deploy, manage, and monitor LLMs in mission-critical production systems.
• Remote & Flexible: Choose your working model—hourly or project-based—from anywhere in the world.
• Future Opportunities: Be matched with projects focused on LLMOps, AI serving, and large-scale AI infrastructure.
• Growth & Recognition: Join a forward-thinking network where your infrastructure skills are valued and continuously in demand.