MLOps Engineer

About the Role: Bright Vision Technologies is seeking an experienced MLOps Engineer to design, build, and operate high-performance infrastructure for serving machine learning models in production. This role focuses on inference platforms for large language models (LLMs), computer vision models, and recommendation systems. You will improve serving performance, optimize GPU resources, build reliable deployment workflows, and maintain observability across AI services. The ideal candidate has strong distributed systems and performance engineering expertise and understands how to balance latency, throughput, reliability, and operating costs.

Responsibilities: Design and operate model-serving platforms for LLMs, computer vision models, and recommendation systems. Optimize inference performance using techniques such as continuous batching, paged attention, speculative decoding, and request multiplexing. Implement multi-tenant request routing, rate limiting, and quality-of-service policies across model endpoints. Develop autoscaling and capacity management systems that balance latency, throughput, and cost. Optimize GPU utilization, memory management, and key-value (KV) cache strategies for LLM inference. Integrate model-serving infrastructure with API gateways, identity systems, and observability platforms. Implement caching, prompt deduplication, and response reuse strategies where appropriate. Build end-to-end observability using latency metrics, queue dynamics, GPU utilization measurements, and error tracking. Develop deployment workflows that support canary releases, shadow testing, and automated rollbacks. Participate in incident response for highly available AI services and implement long-term reliability improvements. Collaborate with machine learning and product teams to support new model releases and capability rollouts. Implement serving-layer security controls, including request signing, content filtering, and abuse detection. Document operational procedures, performance characteristics, and optimization guidance for internal teams. Monitor developments in AI serving research and apply relevant improvements to production systems.

Qualifications: Bachelor's or master's degree in computer science or a related field.

Required Skills: At least 6 years of experience in distributed systems, infrastructure, or ML platform engineering. Strong proficiency in Python and a systems programming language such as Go, Rust, or C++.Extensive experience operating high-throughput, low-latency services in production. Hands-on experience with large-model inference frameworks such as vLLM or TensorRT-LLM.Strong understanding of GPU architecture, memory hierarchies, and accelerator utilization. Familiarity with Kubernetes, autoscaling, and modern cloud platforms. Experience with observability tools and practices, including metrics, tracing, and structured logging. Strong knowledge of performance engineering and capacity planning. Effective communication skills and experience responding to production incidents.

About the Role: Work Location This is a fully remote, full-time W-2 position for candidates located in the continental United States. The role is an in-house Statement of Work (SOW) engagement with Bright Vision Technologies. Employment Terms Direct W-2 employment with Bright Vision Technologies is required. C2C, 1099, and third-party arrangements are not accepted. New H-1B sponsorship is not available. Candidates with a valid H-1B visa who require a transfer may apply, and transfers are supported for qualified candidates. A technical coding assessment is mandatory.

Equal Opportunity Statement: Equal Employment Opportunity Bright Vision Technologies is an equal opportunity employer. The company prohibits discrimination and harassment and provides equal employment opportunities in accordance with applicable federal, state, and local laws.