MLOps Engineer

About the role

First Tech is seeking an MLOps Engineer to design, build, and operate the infrastructure that powers large‑language‑model (LLM) applications in production. You will work on GPU‑backed inference, secure deployment pipelines, and end‑to‑end ML workflows across multiple cloud providers.

Key responsibilities

• Deploy, scale, and maintain Kubernetes clusters running GPU‑backed LLM workloads.
• Architect and provision multi‑cloud infrastructure using Terraform.
• Optimize LLM inference for latency, throughput, and cost, including quantization and batching.
• Build CI/CD pipelines for containerized services and manage retrieval/caching layers.
• Monitor system health, lead incident response, and enforce security and compliance controls.

Required profile

• 3+ years of experience in MLOps, LLMOps, DevOps, or platform engineering.
• Strong knowledge of container orchestration, GPU scheduling, and autoscaling.
• Proficiency with at least one major cloud (AWS, GCP, or Azure) and IaC tools like Terraform.
• Understanding of cloud security fundamentals (IAM, VPC, encryption, audit logging).
• Experience with observability practices (logging, monitoring, tracing, SLO management).

Required skills

• Kubernetes
• Terraform
• AWS, GCP, Azure
• GPU scheduling and node pool design
• LLM inference serving frameworks (e.g., vLLM, TGI, Triton)
• Inference optimization techniques (quantization, batching, KV‑cache)
• Observability tools and practices
• Cloud security and compliance controls

What we offer

• Competitive salary and performance‑based incentives
• Health and wellness support
• Career development and learning opportunities
• Exposure to high‑impact projects and cross‑functional teams
• A collaborative culture that encourages innovation and ownership