Top Vector Database Engineers

Experienced AI/ML Engineer with 9+ years driving the design, deployment, and operationalization of scalable machine learning and Generative AI platforms across cloud-native environments (GCP & AWS). Specialized in LLMOps, retrieval-augmented generation (RAG), and multimodal AI using cutting-edge technologies like LangChain, Hugging Face Transformers, Vertex AI, and Stable Diffusion. Proven track record in fine-tuning and deploying advanced LLMs including LLaMA2, Mistral, Gemini, and PaLM API, building secure, high-performance model serving infrastructures with BentoML, KServe, and Ray on Kubernetes. Passionate about bridging innovation and production excellence to deliver intelligent document processing, semantic search, and end-to-end MLOps solutions. Led large-scale LLM deployment projects involving distributed model inference using Ray on Kubernetes clusters / Built centralized prompt orchestration systems using PromptLayer for reusable, optimized prompt engineering / Integrated monitoring and drift detection in production using Evidently AI, Prometheus, and Grafana / Designed secure document retrieval systems using RAG pipelines integrated with enterprise-grade IAM / Delivered serverless scoring and reporting pipelines using Cloud Scheduler, AWS Lambda, and Cloud Run / Developed explainable AI workflows using SHAP and LIME for compliance and stakeholder transparency / Built scalable multi-model serving platforms with support for parallel inference across GPUs / Automated data validation, schema enforcement, and transformation for structured and unstructured data / Architected feature stores using Feast and BigQuery to serve real-time and batch ML models / Migrated legacy ML infrastructure to cloud-native architectures using Terraform and Kubernetes / Standardized deployment workflows using TFX for lifecycle tracking, evaluation, and rollout governance / Maintained compliance-aligned ML documentation and operational playbooks across regulated domains / Developed RESTful and serverless APIs for LLM, NLP, and vision models with FastAPI and Flask

Charles Xie is the founder and CEO of Zilliz, where he focuses on building next-generation database and search technologies for AI applications. At Zilliz, he also invented Milvus, the world's most popular open-source vector database for production-ready AI.

AI Software and Backend Engineer with 3+ years of experience building scalable services, LLM-driven applications, and machine-learning workflows across enterprise and product environments. Skilled in Python, Java, Node.js, FastAPI, Spring Boot, TensorFlow, PyTorch, Docker, Kubernetes, PostgreSQL, Redis, and cloud-based deployments. Experienced in developing REST APIs, vector-search pipelines, model-serving systems, and automated data workflows supporting high-volume production workloads. Proven ability to optimize performance, reduce operational overhead, and deliver reliable system behavior using observability tools, CI/CD practices, and modern engineering standards.

Generative AI / LLM/ NLP Data Scientist with 15+ years of experience.

Portfolio: https://ausafmo.comG5 AI Studio: https://aistudio.galleri5.comAI platform engineer at Galleri5, part of Collective Artists Network, working on G5 AI Studio - a production AI content platform for ads, microdramas, shows, and films.I build and operate agentic AI systems across brief interpretation, workflow planning, generation, editing, validation, review, and long-running execution.My work spans product and infrastructure: specialist-agent orchestration, typed tool execution, evals/validators, workflow state, real-time streaming, inference routing, GPU dispatching, and production reliability.These systems have powered production AI content workflows including AI Mahabharat on JioHotstar and Chiranjeevi Hanuman, which premiered on IMAX and crossed 8M+ YouTube views.Key systems I've built or own: -> Agentic workflow runtime for G5 AI Studio: Built the end-to-end agentic workflow module that turns creative briefs into executable production flows covering planning, specialist-agent orchestration, dynamic tool registry, typed tool execution, evals/validators, streaming state, and human-in-the-loop review. -> Multi-model inference platform: Built the GPU Dispatcher that evolved into the Inference Gateway, now routing 80+ models across 7 providers including external APIs and internal H100 GPU capacity. The system handles WRR scheduling, provider failover, model routing, Redis queues, lease-based concurrency, retry handling, WAL recovery, production monitoring, and manifest-driven onboarding. -> AI asset platform work with Microsoft: Versioned storage, semantic retrieval, automated quality evaluation, preference-aware ranking, and real-time review workflows.Earlier work: Built ML and data pipelines for Galleri5's Social Intelligence and Trends Intelligence products: semantic product search across millions of SKUs, sentence-transformer classification, real-time Pinecone upsertion, async ingestion pipelines, trend discovery, product curation, catalog enrichment, deduplication, clustering, and forecasting across social, media, creator, and commerce datasets.Tech: Python, FastAPI, PyTorch, LangChain, Microsoft Agent Framework, Gemini, Claude, OpenAI, ComfyUI, MongoDB, Redis, Pinecone, Docker, GCP, Azure, AWS, RunPod, Replicate.

Experienced with a demonstrated history of working in the information technology and Product industry. Skilled in Hadoop,Hive, HBase, Superset,Druid,Pig, Presto,Trino,Nifi ,Apache Hadoop, Hortonworks and Cloudera. Strong information technology professional with a Master of Science (M.Sc.) focused in Innovative Technology from University of East London.