Senior AI Engineer (AI)

TL;DR

Senior AI Engineer (vLLM/RAG): Designing and operating enterprise AI systems across a client portfolio with an accent on inference optimization and end-to-end AI stack implementation. Focus on tuning LLM inference serving, architecting RAG pipelines, and managing high-performance GPU infrastructure.

Location: Must be based in Atlanta, United States

Compensation: $180,000 - $200,000 per year

Company

hirify.global is a leading provider of IT services and solutions specializing in cloud, cybersecurity, infrastructure, and application modernization for enterprise clients.

What you will do

• Lead end-to-end design and operation of AI systems on AI Factory platforms such as HPE PCAI, Dell AI Factory, and Nutanix Enterprise AI.
• Engineer and tune LLM inference serving stacks, specifically utilizing vLLM for optimal latency, throughput, and cost.
• Architect RAG applications with vector databases, focusing on chunking strategies, retrieval tuning, and context-window management.
• Develop MLOps pipelines covering the model lifecycle, registries, deployment, and observability.
• Engineer high-performance storage and networking for AI workloads using RDMA fabrics and parallel filesystems.
• Collaborate directly with client architects and executives to deliver production AI outcomes and provide technical mentorship.

Requirements

• 7+ years of software, data, or infrastructure engineering, with 3+ years specialized in modern AI/LLM systems.
• Production-level proficiency in Python, deep Linux system internals, and Docker.
• Hands-on experience deploying and operating vLLM and AI Factory platforms (HPE, Dell, or Nutanix).
• Practical experience with vector databases, RAG pipelines, and production-scale prompt engineering.
• Demonstrated ability to design LLM evaluation harnesses and quality metrics.
• Location: Based in Atlanta, United States

Nice to have

• Experience with GPU drivers, CUDA toolchains, and NVIDIA AI Enterprise software stack.
• Familiarity with Ray for distributed training and inference scaling.
• Certified Kubernetes Administrator (CKA) or CKAD certifications.
• Knowledge of LoRA/QLoRA/PEFT and supervised fine-tuning workflows.
• Experience with Infrastructure as Code (Terraform, Ansible, Helm).

Culture & Benefits

• Opportunity to work at the center of enterprise AI investment and cutting-edge AI Factory platforms.
• High-impact role with direct engagement across a diverse client portfolio.
• Commitment to technical excellence through mentorship and continuous practice improvement.
• Collaborative environment focused on conquering IT complexity through innovation.