Looking for a job

Eric Lucas

@ericlucas

Message

Senior Software Engineer specializing in LLM inference optimization, RAG, and production AI platforms.

United States

Message

What I'm looking for

I’m looking to build secure, governed, production AI—optimizing LLM inference and RAG for low latency and strong reliability. I want to ship scalable distributed systems and full-stack platforms with measurable performance and safety gains.

I’m a Senior Software Engineer with 10+ years of experience building and scaling high-throughput distributed systems and AI infrastructure. I specialize in LLM inference optimization, RAG architectures, and production-grade full-stack platforms that balance performance, cost, and safety.

Most recently at Together AI, I led end-to-end AI integration of orchestration frameworks and multi-modal frontier models into enterprise products. I built Python/Django/GraphQL microservices, containerized deployments with Docker, and delivered low-latency streaming APIs with SSE and WebSockets—improving user-perceived performance by 35%.

Previously, at Hippocratic AI I developed HIPAA-compliant AI voice agents using LLM orchestration and Twilio, automating 60% of critical healthcare workflows and reducing manual scheduling overhead by 40%. Earlier at Microsoft, I architected scalable Azure/Microsoft 365 backend services, migrated legacy monoliths to microservices, and improved reliability and operational outcomes through observability—while I continue to drive AI governance to reduce hallucinations and support safe deployment.

Experience

Work history, roles, and key accomplishments

Current

Senior Software Engineer

Current

Together AI

Mar 2025 - Present (1 year 3 months)

Led end-to-end AI integration of orchestration frameworks, embedding multi-modal frontier models into existing enterprise products. Built real-time streaming APIs (SSE/WebSockets) improving user-perceived performance by 35% and reduced hallucinations by 30% via model evaluation and AI governance.

Python Django GraphQL Docker SSE WebSockets TypeScript React Redis AI model evaluation

Senior Software Engineer

Hippocratic AI

Feb 2023 - Feb 2025 (2 years)

Developed AI voice agents for healthcare using LLM orchestration and Twilio, automating 60% of critical workflows. Built HIPAA-compliant backend services and full-stack patient workflows (React, Node.js, AWS), reducing manual scheduling overhead by 40%, and mentored 5 engineers.

Orchestration Twilio HIPAA compliance Prompt Engineering React Node AWS

Software Engineer

Microsoft

Apr 2019 - Feb 2023 (3 years 10 months)

Architected scalable Azure and Microsoft 365 backend services in C#, supporting millions of daily requests with 99.99% uptime. Migrated legacy monoliths to microservices, reducing deployment times by 50% and improving reliability, and implemented observability with Azure Monitor to cut MTTR by 50%.

C++Azure Microsoft 365 Microservices azure monitor Observability Reliability Engineering Performance Optimization

Full Stack Developer

CloseLoop Technologies

Jun 2016 - Mar 2019 (2 years 9 months)

Delivered end-to-end SaaS applications using React and Node.js, improving client-facing product performance by 30%. Automated CI/CD pipelines to reduce manual deployment effort by 40%, and engineered scalable RESTful APIs to support complex workflows for a growing user base.

React Node RESTful APIs CI CD Pipelines SaaS Development Performance Optimization