Note: The job is a remote job and is open to candidates in USA. Bright Vision Technologies is a technology consulting and software development company delivering cloud, AI, data, and enterprise solutions across the United States. The AI Platform Engineer will design, build, and operate scalable, reliable, secure, and observable AI inference and machine learning platforms for production workloads. The role focuses on LLM serving, GPU optimization, Kubernetes, cloud infrastructure, MLOps, and collaboration with cross-functional engineering teams.
Responsibilities
- Design and maintain scalable AI model serving platforms
- Optimize inference performance, GPU utilization, and request routing
- Build autoscaling, deployment, and monitoring solutions
- Implement caching, security, and high-availability strategies
- Collaborate with ML teams to deploy and support production AI models
- Design, build, and maintain scalable AI inference and model-serving platforms for enterprise production environments
- Architect highly available, cloud-native infrastructure supporting Large Language Models (LLMs), foundation models, and machine learning services
- Optimize inference latency, throughput, GPU utilization, memory management, and request scheduling across distributed AI workloads
- Design autoscaling, workload orchestration, traffic management, and intelligent request routing strategies for AI services
- Implement model deployment, versioning, rollback, and lifecycle management using modern MLOps practices
- Develop monitoring, observability, logging, distributed tracing, and alerting solutions to ensure platform reliability and performance
- Implement caching strategies, API gateways, security controls, authentication, authorization, and high-availability architectures
- Collaborate with AI researchers, ML engineers, DevOps teams, and software engineers to deploy and support production AI models
- Drive cloud infrastructure optimization, resource utilization, FinOps initiatives, and operational excellence
- Mentor engineering teams, conduct architecture reviews, and establish best practices for AI platform engineering and cloud-native development
- Evaluate emerging AI infrastructure technologies, model-serving frameworks, and GPU acceleration techniques to drive continuous innovation
Skills
- 6+ years of experience in distributed systems, infrastructure, or ML platform engineering
- Strong proficiency in Python and Go, Rust, or C++
- Experience with LLM inference frameworks (vLLM, TensorRT-LLM), Kubernetes, cloud platforms, and GPU optimization
- U.S. Citizens, Green Card Holders, EAD Holders, and H-1B transfer candidates are encouraged to apply
- We are unable to sponsor new H-1B visa petitions for this position
- Bachelor's or Master's degree in Computer Science, Computer Engineering, Artificial Intelligence, or a related technical discipline
- 10+ years of professional experience in distributed systems, infrastructure engineering, cloud platforms, or machine learning platform engineering
- Strong programming skills in Python and at least one systems programming language such as Go, Rust, or C++
- Extensive experience with Large Language Model (LLM) serving, model inference optimization, and production AI infrastructure
- Hands-on experience with vLLM, TensorRT-LLM, Triton Inference Server, Ray Serve, or similar AI serving frameworks
- Strong expertise in Kubernetes, container orchestration, Docker, and cloud-native application architectures
- Experience optimizing GPU workloads using CUDA, NVIDIA GPU technologies, distributed inference, and high-performance AI infrastructure
- Experience with cloud platforms including AWS, Microsoft Azure, or Google Cloud Platform (GCP)
- Strong understanding of distributed systems, networking, scalability, observability, and security best practices
- Excellent analytical, communication, collaboration, and technical leadership skills
- Experience designing and operating multi-region AI platforms and globally distributed inference services
- Knowledge of model optimization techniques such as quantization, pruning, compression, speculative decoding, KV cache optimization, and mixed-precision inference
- Experience with MLOps, GitOps, Infrastructure as Code (Terraform, Bicep, CloudFormation), and CI/CD automation
- Familiarity with service mesh technologies such as Istio or Linkerd, API gateways, and event-driven architectures
- Contributions to open-source AI infrastructure projects, technical publications, patents, or conference presentations
- Experience implementing FinOps strategies, cloud cost optimization, and enterprise AI governance
- Experience with multi-region AI deployments and AI infrastructure
- Familiarity with model optimization techniques such as quantization or compression
- Open-source contributions or experience supporting large-scale AI APIs
Benefits
- 100% Remote (Continental United States)
- Tremendous career growth potential
Company Overview