Senior MLOps Engineer (AI)

Location: Palo Alto, California, United States; on-site

Company

hirify.global is an enterprise AI product and research company building long-running AI agents powered by specialized Small Language Models for financial audit, accounting, and other professional knowledge workflows.

What you will do

• Design, build, and operate end-to-end ML infrastructure covering training orchestration, experiment tracking, model registries, model CI/CD, and automated evaluation.
• Own low-latency, high-throughput LLM and SLM serving infrastructure using batching, caching, and autoscaling.
• Build and manage multi-GPU training and inference clusters across cloud and on-premises environments, including scheduling, utilization, and cost optimization.
• Implement production observability for latency, throughput, model drift, regressions, and quality with actionable alerting.
• Apply inference-time optimizations including quantization, distillation support, KV-cache management, and deployment tuning.
• Harden the platform for enterprise use through reproducibility, versioning, access controls, audit-ready traceability, and MLOps standards.

Requirements

• 5+ years of experience in MLOps, ML infrastructure, or platform engineering with substantial production ownership.
• Production experience deploying and scaling LLM inference infrastructure with serving frameworks such as TRT, vLLM, SGLang, or TGI.
• Strong proficiency with Kubernetes, Docker, and infrastructure as code such as Terraform.
• Hands-on experience managing GPU clusters and distributed training or serving environments.
• Proficiency in Python and experience building maintainable production systems.
• Experience with ML pipelines, orchestration tools, cloud architecture, and a BS degree in computer science or a related technical field.

Nice to have

• MS degree in computer science or a related technical field.
• Experience with multi-node GPU training and quantization techniques such as AWQ, GPTQ, FP8, or GGUF.
• Experience with Spark, Airflow, fine-tuning workflows for LLMs or VLMs, and RLHF or DPO pipelines.
• Experience in regulated or enterprise environments where reliability, security, and auditability are critical.
• Contributions to open-source ML infrastructure projects.

Culture & Benefits

• Work as an early senior infrastructure team member with significant influence over technical foundations and tooling standards.
• Build infrastructure used in real enterprise deployments rather than demonstrations.
• Competitive Silicon Valley-standard salary, significant equity, and premium benefits.
• Collaborate with a team backed by General Catalyst, Walden Catalyst, and Intel.