Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Senior AI Engineer with 8 years of experience building and scaling production AI systems across LLM applications, Retrieval-Augmented Generation (RAG), and AI platform engineering. I design end-to-end solutions including data pipelines, model integration, evaluation, deployment workflows, and production monitoring. I focus on reliability, performance, and cost-efficient AI operations, with strong distributed systems and backend engineering experience. I’ve progressed from AI application development to owning AI architecture, evaluation frameworks, and production AI platforms, including multi-model routing and observability tooling.…Senior AI Engineer with 8 years of experience building and scaling production AI systems across LLM applications, Retrieval-Augmented Generation (RAG), and AI platform engineering. I design end-to-end solutions including data pipelines, model integration, evaluation, deployment workflows, and production monitoring. I focus on reliability, performance, and cost-efficient AI operations, with strong distributed systems and backend engineering experience. I’ve progressed from AI application development to owning AI architecture, evaluation frameworks, and production AI platforms, including multi-model routing and observability tooling.

David Wilson

AI Engineer, Data Scientist, Software Engineer, +4





Senior AI Engineer with 8 years of experience building and scaling production AI systems across LLM applications, Retrieval-Augmented Generation (RAG), and AI platform engineering. I design end-to-end solutions including data pipelines, model integration, evaluation, deployment workflows, and production monitoring. I focus on reliability, performance, and cost-efficient AI operations, with strong distributed systems and backend engineering experience. I’ve progressed from AI application development to owning AI architecture, evaluation frameworks, and production AI platforms, including multi-model routing and observability tooling.…Senior AI Engineer with 8 years of experience building and scaling production AI systems across LLM applications, Retrieval-Augmented Generation (RAG), and AI platform engineering. I design end-to-end solutions including data pipelines, model integration, evaluation, deployment workflows, and production monitoring. I focus on reliability, performance, and cost-efficient AI operations, with strong distributed systems and backend engineering experience. I’ve progressed from AI application development to owning AI architecture, evaluation frameworks, and production AI platforms, including multi-model routing and observability tooling.

Available to hire

Senior AI Engineer with 8 years of experience building and scaling production AI systems across LLM applications, Retrieval-Augmented Generation (RAG), and AI platform engineering. I design end-to-end solutions including data pipelines, model integration, evaluation, deployment workflows, and production monitoring.

I focus on reliability, performance, and cost-efficient AI operations, with strong distributed systems and backend engineering experience. I’ve progressed from AI application development to owning AI architecture, evaluation frameworks, and production AI platforms, including multi-model routing and observability tooling.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Beginner

Work Experience

Senior AI Engineer at Langate

May 2, 2023 - February 2, 2026

Architected scalable AI systems supporting 1M+ users across enterprise and SaaS production environments. Designed multi-model routing and orchestration systems to dynamically select LLMs based on cost, latency, and quality requirements. Developed evaluation, benchmarking, and observability frameworks to measure model performance and production reliability. Implemented AI safety controls including prompt injection detection, response validation, and output filtering. Improved inference performance using caching strategies, batching, asynchronous processing, and distributed execution models. Built AI microservices using Python (FastAPI), Node.js, Spring Boot, and .NET Core within distributed system architectures.

AI Developer at John Howard Perficient

November 1, 2018 - January 1, 2023

Developed AI applications using large language models, integrating APIs into internal tools and customer-facing systems. Built RAG pipelines using embeddings, vector databases, and semantic search to improve response accuracy. Created prompt templates, testing workflows, and evaluation processes to improve consistency and reliability of AI outputs. Developed backend services and APIs using Python (FastAPI), Node.js, PostgreSQL, and Redis to support AI-driven applications. Supported data preparation, model experimentation, and performance tuning to improve inference quality and system behavior.