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

I’m a Senior AI/ML Engineer with 12+ years of experience building production-grade AI systems, scalable backend platforms, and data-driven products. I specialize in Generative AI, LLM applications, RAG pipelines, and AI agents that automate complex workflows and deliver real business value. I’ve worked on AI platforms used by millions of users, including conversational search systems, enterprise automation agents, and safety-critical healthcare AI applications. My work has involved designing end-to-end architectures—from data ingestion and retrieval systems to model orchestration and production deployment on AWS/GCP. What makes me stand out is that I don’t just build AI prototypes—I focus on shipping reliable, scalable systems that actually work in production. I combine strong software engineering fundamentals with deep AI/ML expertise, allowing me to turn complex ideas into robust products that companies can depend on.…I’m a Senior AI/ML Engineer with 12+ years of experience building production-grade AI systems, scalable backend platforms, and data-driven products. I specialize in Generative AI, LLM applications, RAG pipelines, and AI agents that automate complex workflows and deliver real business value. I’ve worked on AI platforms used by millions of users, including conversational search systems, enterprise automation agents, and safety-critical healthcare AI applications. My work has involved designing end-to-end architectures—from data ingestion and retrieval systems to model orchestration and production deployment on AWS/GCP. What makes me stand out is that I don’t just build AI prototypes—I focus on shipping reliable, scalable systems that actually work in production. I combine strong software engineering fundamentals with deep AI/ML expertise, allowing me to turn complex ideas into robust products that companies can depend on.

Tate Savage

AI Engineer, Full Stack Developer, Back-End Developer, +2





I’m a Senior AI/ML Engineer with 12+ years of experience building production-grade AI systems, scalable backend platforms, and data-driven products. I specialize in Generative AI, LLM applications, RAG pipelines, and AI agents that automate complex workflows and deliver real business value. I’ve worked on AI platforms used by millions of users, including conversational search systems, enterprise automation agents, and safety-critical healthcare AI applications. My work has involved designing end-to-end architectures—from data ingestion and retrieval systems to model orchestration and production deployment on AWS/GCP. What makes me stand out is that I don’t just build AI prototypes—I focus on shipping reliable, scalable systems that actually work in production. I combine strong software engineering fundamentals with deep AI/ML expertise, allowing me to turn complex ideas into robust products that companies can depend on.…I’m a Senior AI/ML Engineer with 12+ years of experience building production-grade AI systems, scalable backend platforms, and data-driven products. I specialize in Generative AI, LLM applications, RAG pipelines, and AI agents that automate complex workflows and deliver real business value. I’ve worked on AI platforms used by millions of users, including conversational search systems, enterprise automation agents, and safety-critical healthcare AI applications. My work has involved designing end-to-end architectures—from data ingestion and retrieval systems to model orchestration and production deployment on AWS/GCP. What makes me stand out is that I don’t just build AI prototypes—I focus on shipping reliable, scalable systems that actually work in production. I combine strong software engineering fundamentals with deep AI/ML expertise, allowing me to turn complex ideas into robust products that companies can depend on.

Available to hire

I’m a Senior AI/ML Engineer with 12+ years of experience building production-grade AI systems, scalable backend platforms, and data-driven products. I specialize in Generative AI, LLM applications, RAG pipelines, and AI agents that automate complex workflows and deliver real business value.

I’ve worked on AI platforms used by millions of users, including conversational search systems, enterprise automation agents, and safety-critical healthcare AI applications. My work has involved designing end-to-end architectures—from data ingestion and retrieval systems to model orchestration and production deployment on AWS/GCP.

What makes me stand out is that I don’t just build AI prototypes—I focus on shipping reliable, scalable systems that actually work in production. I combine strong software engineering fundamentals with deep AI/ML expertise, allowing me to turn complex ideas into robust products that companies can depend on.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

R&D Software Engineer at Invisible Technologies

October 1, 2025 - Present

Designed and implemented LLM-powered agentic workflows that combine structured prompting, tool-calling, and retrieval pipelines to automate complex enterprise processes. Built evaluation and benchmarking frameworks for LLM systems, measuring task accuracy, hallucination rates, policy compliance, and structured output consistency. Developed RAG pipelines using embedding-based retrieval and vector databases to ground model outputs in verified enterprise data. Implemented human-in-the-loop review systems, designing fallback, validation, and feedback loops to support RLHF-style continuous model improvement. Built backend services in Python (FastAPI) orchestrating multi-step reasoning chains and integrating third-party APIs within enterprise automation pipelines. Containerized services with Docker and deployed scalable workloads on AWS/GCP using infrastructure-as-code (Terraform) and CI/CD (GitHub Actions). Introduced monitoring and observability using Datadog, improving visibility into mod

Senior AI Software Engineer – Team Lead at Hippocratic AI

March 1, 2023 - October 1, 2025

Built and deployed safety-critical healthcare AI agents powered by large-scale LLMs, automating real patient-facing workflows at production scale. Designed RAG pipelines combining clinical guidelines, payer policies, and EMR data to improve policy-aligned responses accuracy by 15%. Architected multi-agent orchestration systems that handled intake, follow-ups, scheduling, and care coordination with structured outputs and safety guardrails. Integrated real-time voice systems (ASR/TTS + streaming inference) to support multilingual patient conversations with low latency. Developed secure Python microservices and EMR integrations (Epic/Cerner) enabling automated documentation and workflow updates. Implemented evaluation and safety pipelines to reduce hallucinations, enforce compliance, and validate clinical accuracy before rollout. Improved system reliability through monitoring, alerting, retry/fallback logic, and robust CI/CD deployment workflows.

Senior Software Engineer – AI Research at You.com

May 1, 2020 - February 1, 2023

Built RAG pipelines combining hybrid search (BM25 + dense embeddings) with LLM summarization to deliver grounded, conversational answers. Developed backend services in Python and Go, exposing REST and GraphQL APIs using FastAPI and TypeScript, integrating Elasticsearch, Pinecone, and PostgreSQL, improving low-latency query latency by 35%. Implemented LLM orchestration workflows using PyTorch, Hugging Face Transformers (BERT/GPT), and embedding pipelines to support multi-turn conversational experiences. Designed and optimized vector search and ranking systems from 1.8s to 1.1s leveraging Redis caching, async processing, and distributed microservices deployed via Docker and Kubernetes on GCP/AWS. Built CI/CD pipelines with GitHub Actions, infrastructure-as-code using Terraform, and production monitoring with Datadog to ensure reliability at scale. Collaborated with research teams to productionize model experiments into scalable AI assistant features under real user traffic.

Senior Software Engineer | Glossier, Inc at Glossier, Inc

July 1, 2016 - April 1, 2020

Developed backend services in Python (Django/Flask) and Node.js, exposing REST and GraphQL APIs powering product catalog, checkout, and customer workflows. Built frontend features using React and TypeScript, improving performance and user engagement across product and recommendation surfaces. Designed and deployed recommendation systems leveraging behavioral data, embeddings, and analytics pipelines to personalize product discovery. Implemented data pipelines using Airflow, Spark, and dbt, transforming customer interaction data into actionable signals for marketing and merchandising teams. Optimized database performance using PostgreSQL and Redis caching, reducing latency across high-traffic endpoints. Containerized services with Docker, deployed on AWS (ECS, S3) with infrastructure managed via Terraform and CI/CD through GitHub Actions. Introduced monitoring and alerting via Datadog, improving production visibility and incident response.

Full Stack Engineer at PayPal

June 1, 2013 - June 1, 2016

Developed backend services in Java and Python, building RESTful APIs for transaction processing, payment orchestration, and internal financial tools. Built full-stack features using JavaScript (React/Angular) and Node.js, supporting customer-facing payment flows and internal operational dashboards. Integrated fraud detection and risk evaluation services into transaction pipelines, ensuring reliable real-time decisioning under high traffic. Designed and optimized SQL-based data models, improving query performance and maintaining financial data consistency across distributed systems. Implemented caching strategies using Redis to reduce latency across high-frequency endpoints. Participated in production deployments, monitoring, and incident response, maintaining high availability and compliance standards. Collaborated with cross-functional teams including risk, compliance, and product to deliver secure and scalable payment features.

Software Engineer Intern at PayPal

June 1, 2012 - May 1, 2013

Built internal web tools using Java and AngularJS, supporting fraud analytics and operational monitoring teams. Developed RESTful APIs to expose transaction and risk data for internal dashboards. Wrote SQL queries and optimized database access patterns to improve reporting performance. Integrated Elasticsearch for improved search and filtering across transaction datasets. Collaborated with senior engineers on feature development, testing, and production deployment workflows. Participated in code reviews and debugging sessions, strengthening backend and distributed systems fundamentals.