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

I am an AI Full-Stack Engineer specializing in LangChain, LLM integration, and retrieval-augmented generation (RAG), with 10+ years of backend and full-stack experience. I have deployed GPT/LLM-powered FastAPI microservices, built secure AI infrastructure, and optimized retrieval pipelines for clinical and compliance-sensitive environments to improve trust and efficiency. I am passionate about advancing AI in healthcare and helping organizations meet regulatory requirements. I enjoy turning complex AI challenges into reliable products that clinicians can rely on, with a focus on ethical, auditable data handling and user-friendly interfaces.…I am an AI Full-Stack Engineer specializing in LangChain, LLM integration, and retrieval-augmented generation (RAG), with 10+ years of backend and full-stack experience. I have deployed GPT/LLM-powered FastAPI microservices, built secure AI infrastructure, and optimized retrieval pipelines for clinical and compliance-sensitive environments to improve trust and efficiency. I am passionate about advancing AI in healthcare and helping organizations meet regulatory requirements. I enjoy turning complex AI challenges into reliable products that clinicians can rely on, with a focus on ethical, auditable data handling and user-friendly interfaces.

Alexander Lee

Full Stack Developer, AI Engineer, Data Scientist, +4





I am an AI Full-Stack Engineer specializing in LangChain, LLM integration, and retrieval-augmented generation (RAG), with 10+ years of backend and full-stack experience. I have deployed GPT/LLM-powered FastAPI microservices, built secure AI infrastructure, and optimized retrieval pipelines for clinical and compliance-sensitive environments to improve trust and efficiency. I am passionate about advancing AI in healthcare and helping organizations meet regulatory requirements. I enjoy turning complex AI challenges into reliable products that clinicians can rely on, with a focus on ethical, auditable data handling and user-friendly interfaces.…I am an AI Full-Stack Engineer specializing in LangChain, LLM integration, and retrieval-augmented generation (RAG), with 10+ years of backend and full-stack experience. I have deployed GPT/LLM-powered FastAPI microservices, built secure AI infrastructure, and optimized retrieval pipelines for clinical and compliance-sensitive environments to improve trust and efficiency. I am passionate about advancing AI in healthcare and helping organizations meet regulatory requirements. I enjoy turning complex AI challenges into reliable products that clinicians can rely on, with a focus on ethical, auditable data handling and user-friendly interfaces.

Available to hire

I am an AI Full-Stack Engineer specializing in LangChain, LLM integration, and retrieval-augmented generation (RAG), with 10+ years of backend and full-stack experience. I have deployed GPT/LLM-powered FastAPI microservices, built secure AI infrastructure, and optimized retrieval pipelines for clinical and compliance-sensitive environments to improve trust and efficiency.

I am passionate about advancing AI in healthcare and helping organizations meet regulatory requirements. I enjoy turning complex AI challenges into reliable products that clinicians can rely on, with a focus on ethical, auditable data handling and user-friendly interfaces.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

Senior Full-Stack AI Engineer at Tempus

February 1, 2022 - Present

Led development of a retrieval-augmented summarization tool for oncologists using LangChain-based RAG and LLaMa 3/OpenAI models; optimized retrieval with cosine similarity and metadata prefilters, reducing noise and improving factual alignment. Achieved a 60% reduction in clinician-identified hallucinations by tuning chunking, embeddings, and model selection. Improved summary latency from 7.8s to 4.6s via caching, async FastAPI endpoints, and streamlined I/O. Built ML-based ranking/filtering (XGBoost + embedding similarity) increasing domain F1 from 0.73 to 0.88. Implemented PHI-masking and IAM access with AWS Secrets Manager for HIPAA compliance, and deployed an MCP server to standardize secure internal retrieval tools for agentic LLM workflows. Developed React components to visualize retrieved context and model outputs, and FastAPI REST APIs with async streaming for trace dashboards. Contributed to a 500K pathology report search/retrieval API using Pinecone and hybrid keyword/search,

Software Engineer / Consultant at Manifest Solutions

May 1, 2018 - February 1, 2022

Contributed to an AI-assisted document review system for a legal compliance client; built FastAPI services for document ingestion, parsing, and AI query routing. Led modernization of legacy backend to AWS-based containerized microservices, enabling scalable deployments. Implemented real-time dashboard updates via WebSockets and React, supported frontend integration for displaying extracted clauses and AI insights, and optimized CI/CD pipelines for reliable cross-environment deployments. Created data transformation pipelines for unstructured contracts and designed PostgreSQL schemas for efficient querying of clauses and metadata; leveraged secure S3/EC2 storage with IAM controls. Gained early exposure to classical ML concepts (scikit-learn) for document classification and feature extraction.

Junior Developer / Implementation Engineer at Team Dynamix

August 1, 2014 - April 1, 2018

Developed frontend interfaces with HTML, CSS, and JavaScript to improve usability of internal ticketing and reporting systems. Participated in backend API development with Node.js/PHP, gained full-stack experience, implemented data validation and unit tests to reduce input errors (~20%), performed data migration and normalization for legacy systems, and contributed to admin dashboards with charts and tables for visibility into ticket trends and usage metrics.

Senior AI Full-Stack Engineer at Tempus

February 1, 2022 - Present

Developed LangChain-based RAG pipelines using LLaMA 3 and OpenAI GPT-4, powering clinician-facing summarization tools and improving factual alignment. Built a secure Model Context Protocol (MCP) server to expose internal retrieval tools and validation utilities to agentic LLM workflows, standardizing compliance and traceability. Achieved 60% reduction in clinician-reviewed hallucinations by tuning chunking, embeddings, and model selection. Contributed to a search and retrieval API over 500K pathology reports using Pinecone vector indexes and hybrid keyword embedding search. Optimized retrieval flow by re-ranking chunk relevance with cosine similarity signals and applying metadata prefilters, reducing noise in context assembly and improving factual alignment in generated summaries. Built FastAPI-based REST APIs with async streaming to push retrieval and generation traces to internal dashboards. Optimized caching strategy and implemented async FastAPI endpoints to handle concurrent LLM r