MLOps Engineer (AI)

Location: 100% remote within the Continental United States

Salary: $100K–$150K annually

Company

hirify.global is a software development company building scalable, secure, and user-friendly solutions that automate and optimize business operations.

What you will do

• Design and operate model-serving platforms for LLMs, vision models, and recommendation systems.
• Optimize inference performance through continuous batching, paged attention, speculative decoding, request multiplexing, caching, and prompt deduplication.
• Build multi-tenant routing, rate limiting, quality-of-service policies, autoscaling, and capacity management systems.
• Tune GPU utilization, memory management, and KV-cache strategies for large-model serving workloads.
• Integrate serving platforms with API gateways, identity systems, observability tools, and security controls.
• Develop canary releases, shadow testing, automated rollback, incident response procedures, and reliability improvements for high-availability AI services.

Requirements

• Bachelor’s or Master’s degree in Computer Science or a related field.
• 6+ years of experience in distributed systems, infrastructure, or ML platform engineering.
• Strong proficiency in Python and a systems language such as Go, Rust, or C++.
• Experience operating high-throughput, low-latency production services and large-model inference frameworks such as vLLM or TensorRT-LLM.
• Strong understanding of GPU architecture, memory hierarchies, accelerator utilization, performance engineering, and capacity planning.
• Experience with Kubernetes, autoscaling, cloud platforms, observability stacks, communication, and incident response.

Nice to have

• Open-source contributions to model-serving infrastructure.
• Experience with multi-region or globally distributed AI serving.
• Knowledge of model quantization, distillation, compression, FinOps, or external-facing AI APIs.

Culture & Benefits

• Full-time direct W2 employment with hirify.global.
• In-house Statement of Work engagement with no third-party client, vendor, or implementation partner.
• No C2C or 1099 arrangements.
• No new H1B sponsorship is available; qualified candidates with a valid H1B may receive transfer support.
• Career growth opportunity within an established software development organization.

Hiring process

• A technical coding assessment is mandatory.
• Applications are submitted with a resume for consideration.