MLOps Engineer

Bright Vision Technologies•Sugar Land, TX

17h•$100,000 - $150,000•Remote

About The Position

Bright Vision Technologies is seeking an MLOps Engineer to design, build, and operate high-performance, reliable inference platforms for production machine learning models. The role focuses on the systems engineering of AI deployment, including request routing, batching, caching, autoscaling, GPU utilization, and end-to-end observability across diverse model workloads. The successful candidate will bring distributed-systems and performance-engineering expertise, experience shipping serving systems at scale, and an understanding of trade-offs among latency, throughput, cost, and quality in ML serving. This is a 100% remote, full-time, direct W2 role with Bright Vision Technologies, based in the continental United States. It supports the company’s in-house Statement of Work engagement; Bright Vision Technologies is the client, end customer, and employer, with no third-party client, vendor, or implementation partner involved. C2C, 1099, and other third-party arrangements are not accepted. New H1B sponsorship is unavailable, but qualified candidates with a valid H1B visa who require a transfer may apply. A technical coding assessment is mandatory.

Requirements

Bachelor’s or Master’s degree in Computer Science or a related field.
Six or more 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++.
Deep experience operating high-throughput, low-latency services in production.
Hands-on experience with LLM or 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 stacks, including metrics, tracing, and structured logging.
Solid grounding in performance engineering and capacity planning.
Strong communication and incident-response skills.
Candidates must be willing to work directly as a full-time W2 employee and contribute to in-house SOW deliverables.
A technical coding assessment is mandatory.
No new H1B sponsorship is available; candidates currently on a valid H1B visa who require a transfer may apply.

Nice To Haves

Open-source contributions to model-serving infrastructure.
Experience with multi-region or globally distributed AI serving.
Familiarity with model quantization, distillation, and compression techniques.
Exposure to FinOps for AI workloads and cost-efficient serving design.
Experience supporting external-facing AI APIs at scale.

Responsibilities

Design and operate model-serving platforms for LLMs, vision models, recommendation systems, and other workloads.
Optimize inference performance using continuous batching, paged attention, speculative decoding, and request multiplexing.
Implement multi-tenant routing, rate limiting, and quality-of-service policies across model endpoints.
Build autoscaling and capacity-management systems that balance latency, throughput, and cost.
Tune GPU utilization, memory management, and KV cache strategies for LLM serving workloads.
Integrate model serving with API gateways, identity systems, and observability platforms.
Implement caching, prompt deduplication, and response-reuse strategies where appropriate.
Drive end-to-end observability, including latency histograms, queue dynamics, GPU utilization, and error tracking.
Develop deployment workflows, including canary releases, shadow testing, and automated rollback.
Operate incident response for high-availability AI services and drive durable reliability improvements.
Collaborate with ML 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 tuning guidance for internal teams.
Stay current with AI serving research and translate advances into production capabilities.