N
Nikone Bounyavong
About
Detail
Vientiane, Vientiane Prefecture, Laos
Résumé
Jobs
verified_user
0% verified
Senior AI Infrastructure EngineerHugging FaceOct 2024 - Jan 2026 (1 year 4 months)Enterprise LLM Deployment & RAG Orchestration Platform
Led the architecture and implementation of a Kubernetes-native LLM serving platform enabling enterprise clients to deploy fine-tuned transformer models with secure multi-tenant isolation and autoscaling GPU workloads.
• Architected a distributed model-serving layer using FastAPI + gRPC, integrating GPU-backed inference pods on AWS EKS, reducing inference latency from 1.4s to 480ms (65% improvement).
• Designed and deployed a multi-source RAG pipeline using LangChain and FAISS, supporting document ingestion of 10M+ embeddings while maintaining sub-200ms vector retrieval latency.
• Implemented intelligent request routing with async batching, improving throughput by 2.8- Senior AI Backend EngineerToptalApr 2021 - Aug 2024 (3 years 5 months)Scalable AI Knowledge Intelligence Platform
Delivered production-grade AI infrastructure for multiple high-growth startups, focusing on LLM-based systems, real-time data pipelines, and evaluation tooling.
• Designed a modular RAG framework integrating Pinecone and Weaviate, serving 500k+ monthly AI-driven queries.
• Built secure document ingestion pipelines using async workers and Redis queues, increasing processing throughput by 3x.
• Deployed containerized ML services on Kubernetes clusters with autoscaling policies based on queue lag and GPU utilization.
• Optimized PostgreSQL indexing and caching strategies, reducing API response times by 52%.
• Developed CI/CD pipelines via GitHub Actions enabling zero-dow - AI Platform EngineerAleph AlphaJun 2017 - Feb 2021 (3 years 9 months)Multilingual Transformer Inference Infrastructure
Contributed to the backend architecture of a high-performance transformer inference platform supporting multilingual enterprise AI applications.
• Designed containerized inference services using Docker and Kubernetes, achieving 99.95% service availability.
• Implemented async model-serving patterns with request batching and caching layers, improving throughput by 2x.
• Developed internal evaluation frameworks to benchmark model drift and performance degradation.
• Built scalable data ingestion pipelines using event-driven processing patterns for large-scale training datasets.
• Optimized GPU memory allocation strategies, reducing OOM incidents by 80%.
• Col - LBackend EngineerLao IT DevOct 2014 - Apr 2017 (2 years 7 months)Distributed Data Processing & API Platform
Developed backend services and distributed processing systems for enterprise digital platforms in Laos.
• Built RESTful APIs using Django serving 100k+ monthly active users.
• Implemented Redis caching reducing database load by 45%.
• Designed SQL optimization strategies improving query performance by 40%.
• Introduced containerization practices (Docker), modernizing deployment workflows.
• Collaborated in a 6-person engineering team, contributing to architecture discussions and backend design standards.
Education
verified_user
0% verified
- Bachelor's Degree in Computer ScienceNational University of LaosMay 2010 - Sep 2014 (4 years 5 months)Vientiane, Laos
Awards
verified_user
0% verified
- CCertified Kubernetes Administrator (CKA)Jan 2020
- AAWS Certified Solutions Architect - AssociateJan 2019
- HHackerRank Production debugging (Basic)