Open to opportunities

I jason User

@ijasonuser

Senior AI/ML Engineer specializing in LLMs, RAG, and agentic systems to deliver scalable, production-grade intelligence.

United States

Message

What I'm looking for

I’m looking to build production-grade LLM/ML systems with strong MLOps/LLMOps—CI/CD, evaluation, monitoring, and low-latency performance—delivering measurable business impact through scalable, modular architectures and cross-functional collaboration.

I’m a Senior AI/ML Engineer with 7+ years building and deploying scalable machine learning and generative AI systems across FinTech, AI SaaS, and healthcare. I specialize in LLMs, RAG pipelines, and agentic AI systems, delivering production-grade solutions that enable intelligent automation and data-driven decision making.

I design end-to-end AI systems—integrating traditional ML with LLMs—and I’m especially focused on MLOps/LLMOps practices like CI/CD, model and prompt versioning, evaluation, and monitoring. In my recent roles, I’ve deployed low-latency FastAPI/REST/gRPC services and architected modular RAG solutions using vector databases and embeddings to improve relevance, reduce hallucinations, and support measurable business impact.

Experience

Work history, roles, and key accomplishments

Current

Senior Applied AI Engineer

Current

OctoAI

Jun 2023 - Present (2 years 11 months)

Designed and deployed LLM-powered applications using RAG and agentic workflows to improve response accuracy and automate complex business processes. Owned end-to-end AI lifecycle (ETL/data ingestion, model integration, APIs, and production deployment) with LLMOps practices, low-latency FastAPI/REST-gRPC backends, and AWS containerized deployment.

Agentic AI ETL Vector Databases LLMOps CI CD For ML fastAPI gRPC

AI/ML Engineer

Vertex AI Systems

Jan 2021 - Dec 2022 (1 year 11 months)

Built end-to-end RAG systems for financial and healthcare data to deliver more accurate, context-aware AI responses. Implemented multi-agent workflows and low-latency production APIs with evaluation frameworks/guardrails to reduce hallucinations and improve trust, while optimizing model selection, prompts, and overall cost.

Evaluation Guardrails Cost Optimization

Machine Learning Engineer

Sift

Jun 2018 - Dec 2020 (2 years 6 months)

Developed and deployed machine learning models for fraud detection, forecasting, and anomaly detection across healthcare and financial datasets. Built scalable data pipelines and real-time AWS inference systems, implemented MLOps (CI/CD, model versioning, automated retraining), and monitored performance and drift to improve production reliability.

Fraud Detection Forecasting Anomaly Detection Data Pipelines MLOps Model Versioning Monitoring For Drift

Agentic AI Engineer

Reworkd AI

Jul 2017 - May 2018 (10 months)

Built and orchestrated multi-agent AI systems (retrieval, reasoning, and action agents) and delivered high-precision RAG pipelines tailored to data and use cases. Implemented benchmarking and evaluation frameworks, human-in-the-loop workflows, and observability to improve reliability and trust, while optimizing LLM utilization for cost/latency/output quality and deploying scalable infrastructure w

Benchmarking Human In The Loop Observability Vector Databases