MLOps Engineer

Role Overview

Bright Vision Technologies is seeking an MLOps Engineer to design, build, and operate high-performance ML inference platforms for production. This is a 100% remote role (Continental United States) focused on the systems engineering side of AI deployment, including reliability, routing, batching, caching, autoscaling, GPU utilization, and end-to-end observability.

Responsibilities

• Design and operate model serving platforms for diverse workloads (LLMs, vision models, recommendation systems)
• Optimize inference performance using techniques such as:
  • continuous batching
  • paged attention
  • speculative decoding
  • request multiplexing
• Implement multi-tenant routing, rate limiting, and QoS policies across model endpoints
• Build autoscaling and capacity management systems balancing latency, throughput, and cost
• Tune GPU utilization, memory management, and KV cache strategies for LLM serving
• Integrate serving with API gateways, identity systems, and observability platforms
• Apply caching, prompt deduplication, and response reuse strategies where appropriate
• Drive end-to-end observability (latency histograms, queue dynamics, GPU utilization, error tracking)
• Build deployment workflows: canary releases, shadow testing, automated rollback
• Participate in incident response and implement durable reliability improvements
• Collaborate with ML and product teams on new model releases and capability rollouts
• Add security controls at the serving layer (e.g., request signing, content filtering, abuse detection)
• Document operational procedures and performance/tuning guidance
• Stay current with AI serving research and translate advances into production

Requirements

• Bachelor’s or Master’s degree in Computer Science (or related field)
• 6+ years of experience

Notes / Policy

• Full-time, direct W2 employment through Bright Vision Technologies (in-house SOW engagement)
• No C2C/1099 arrangements
• No new H1B sponsorship; H1B transfers may be supported for qualified candidates
• Technical coding assessment is mandatory

Nice-to-haves

No additional nice-to-have skills were specified in the provided text.