Open to opportunities

Long Tan

@longtan

Message

Senior AI Engineer building trustworthy LLM agents, RAG, and evaluation frameworks.

United States

Message

What I'm looking for

I want to build trustworthy, production-ready agentic LLM systems—prioritizing rigorous evaluation, automated benchmarking, and reliable monitoring. I’m excited to work where engineering standards, human-centered design, and continuous improvement drive real customer impact.

I’m a Senior AI Engineer with 8+ years of experience building production software systems and AI-powered applications. I specialize in Large Language Models (LLMs), agentic workflows, Retrieval-Augmented Generation (RAG), and AI evaluation frameworks that improve quality and reliability over time.

I design AI systems that move from prototype to production by combining model experimentation, evaluation methodologies, backend engineering, monitoring, and continuous improvement loops. I focus on measurable outcomes—automated benchmarks, golden dataset management, regression testing, failure analysis, and human-in-the-loop evaluation to strengthen AI behavior.

In my recent roles, I built production LLM-powered applications and AI automation workflows, including agent-based systems integrating language models with enterprise tools and data sources. I also developed RAG architectures—retrieval pipelines with embeddings, vector search, and document processing—and created evaluation datasets and testing frameworks for response quality.

I’ve also led and founded AI-focused engineering efforts as Co-Founder / CTO and Head of Engineering, establishing standards for testing, monitoring, and reliability while mentoring engineers and partnering with product teams. My goal is to deliver intelligent automation and generative AI products that solve real customer problems through rigorous engineering and human-centered design.

Experience

Work history, roles, and key accomplishments

Current

AI Engineer

Current

Hirevue

Mar 2026 - Present (4 months)

Build production LLM-powered applications and AI automation workflows, including agent-based systems that integrate language models with enterprise tools and data sources. Design AI evaluation approaches to measure quality, reliability, and user impact.

Language Models AI Agents Workflow Agents LLM Evaluation Automated Testing Retrieval Tuning Backend Services

Senior AI/ML Engineer

Hireguide

May 2025 - Mar 2026 (10 months)

Designed and developed LLM applications using RAG architectures and AI workflow automation. Built retrieval pipelines, created evaluation datasets/testing frameworks, and developed APIs and backend services for AI-powered products.

Retrieval Augmented Generation (RAG)Embeddings Vector Search Document Processing LLM Evaluation Testing Frameworks API Development Backend Services

Co-Founder / CTO

Penfield.AI

May 2024 - May 2025 (1 year)

Founded and built AI-powered software products using LLMs and intelligent automation. Designed agent architectures for reasoning, retrieval, and workflow execution, including evaluation processes to validate AI behavior before production releases.

AI Agents Agent Architectures Retrieval Products Intelligent Automation LLM Applications LLM Evaluation Benchmarking Customer Discovery

Head of Engineering

Penfield.AI

Aug 2023 - Jun 2024 (10 months)

Led engineering initiatives for AI product development, including scalable architectures for AI services and data platforms. Established testing, monitoring, and reliability standards, mentored engineers, and partnered with product teams to translate customer requirements into technical solutions.

AI Services Scalability Standards Monitoring Reliability Engineering System Design Mentoring Engineers

Lead Software Engineer

Penfield.AI

Aug 2021 - Apr 2024 (2 years 8 months)

Developed backend systems and APIs supporting intelligent applications and complex business workflows. Designed data models and integrations and improved reliability through testing and performance optimization.

Backend Data Modeling Integration Reliability Engineering Unit Testing Performance Optimization System Design

Senior Software Engineer

Wattpad

Jun 2018 - Aug 2021 (3 years 2 months)

Built scalable backend services for high-volume applications, designing APIs and distributed systems along with data processing workflows. Improved reliability using engineering best practices and collaborated cross-functionally to deliver production features.

Backend Services API Development Distributed Systems Data Processing Reliability Engineering Cross Functional Collaboration