About Me
Welcome! I'm Alexa Griffith, a Senior Principal Software Engineer specializing in AI infrastructure and cloud-native platforms. I focus on building distributed systems for machine learning and gen AI inference at scale, working primarily on platform architecture and infrastructure reliability. Outside of work, I write technical posts and host a podcast called Alexa's Input (AI) (Spotify) where I interview leaders and innovators transforming the tech industry.
I'm currently at Red Hat as a Senior Principal Software Engineer and Forward Deployed Engineer, working directly with engineering teams to design, optimize, and operate production AI systems in real-world environments. I build and deploy large-scale LLM inference systems, focusing on distributed serving, optimization, and inference infrastructure using open source tools like vLLM, llm-d, KServe, and Envoy AI Gateway.
At Bloomberg, I was on the AI Inference Platform team, focused on building platforms that help teams deploy and serve machine learning and gen AI models at scale. My main work involved KServe, a CNCF project for serving predictive and GenAI models on Kubernetes, and Envoy AI Gateway, which manages traffic routing for AI services.
At Bluecore in NYC, I started out helping data scientists operationalize their models. I maintained Airflow, built DAG workflows, and worked on their recommendations service. Later, I joined a new Analytics Infrastructure team where I built a high-throughput, low-latency Go API on Kubernetes, implemented authentication for microservices, and designed and built features for the streaming platform.
I graduated magna cum laude in Honors Chemistry (American Chemical Society certified) and a minor in Spanish from the University of Tennessee, Knoxville in May 2019. I was a Melaven-Rhenium Scholar and 2017 Research in Arts Scholar. During undergrad, I worked on computational chemistry research with Dr. Konstantinos Vogiatzis, focusing on quantum chemistry methods and computational modeling. I conducted interdisciplinary research on the chemistry of blue pigments inspired by studying art history in Paris. I also interned at Oak Ridge National Lab through the DOE SULI program with Dr. Dmytro Bykov, where my research on enzyme catalysis resulted in a published paper in Physical Chemistry Chemical Physics and won a SETCA 2019 Poster Award, and at Technische Universität Kaiserslautern in Germany through the DAAD RISE program with the van Wüllen research group.
Where to Find Me
| Connect | LinkedIn X Instagram TikTok |
|---|---|
| Listen & watch | Alexa’s Input Spotify YouTube |
| Read | Substack Medium |
| All links | Linktree ↗ |
Podcasts
Alexa's Input (AI)
Conversations with engineers and open-source leaders.
Latest episode: Building the Network for AI Agents with Yan Avlasov.
Attention Deficit
Weekly AI news with Alexa Griffith and Taylor Dolezal.
Organizations
- Ambassador - Merge Forward
- Judge - Tetrate Buildathon (June 2026)
- Program Committee Member - Cloud Native AI + Inference Day (KubeCon + CloudNativeCon NA 2026)
- Program Committee Member - AI + ML + Agentic AI + Data Systems Track (KubeCon + CloudNativeCon + OpenInfra Summit + PyTorch Conference China 2026)
- Program Committee Member - AI + ML Track (Kubecon Japan 2026)
- Program Committee Member - Cloud Native AI + Kubeflow Day (Kubecon EU 2026)
- Technical Advisory Group (TAG) Infrastructure Tech Lead - CNCF
- Advisory Panel Member - Cloud Native Platform Engineer (CNPE) Advisory Council
- Program Committee Member - EnvoyCon (Virtual)
- Program Committee Member - Cloud Native + Kubernetes AI Day (Kubecon NA 2025)
- Lead Subject Matter Expert - Cloud Native Platform Associate (CNPA) Advisory Council
Guest Appearances & Interviews
Talks
2026
- Fork Yeah: Choosing Your Own Adventure in Open Source - Alexa Griffith [Women+ in Open Source Forum, New York]
- Embracing the Cringe: 7 Lessons from 70 Interviews - Alexa Griffith [Red Hat EMEA Remote Site Committee Lightning Talks]
- Dashboards & Dragons: Reliability Magic for AI Platforms - Alexa Griffith & Sal Furino [Google SRE Meetup]
- Tools Powering the Age of GenAI - Erica Hughberg (Tetrate) & Alexa Griffith (Red Hat) [Datum Alt Cloud Meetup]
2025
- Inference Awakens: Tools for the Age of GenAI - Alexa Griffith & Erica Hughberg [Kubecon NA]
- Dashboards & Dragons: Reliability Magic for AI Platforms - Alexa Griffith & Sal Furino [SRECon EU]
- Keynote: Platform Alchemy: Transforming Kubernetes Into Generative AI Gold [Kubecon Japan]
- Dashboards Dragons: Crafting SLOs To Tame the AI Platform Chaos - Alexa Griffith & Gavin Li [KubeCrash Spring]
- Serving the Future: KServe’s Next Chapter Hosting LLMs & GenAI Models - Alexa Griffith & Tessa Pham [Kubecon EU AI Day]
- The Explorer’s Guide To Cloud Native GenAI Platform Engineering - Max Körbächer & Alexa Griffith [Kubecon EU]
- Dashboards & Dragons: Crafting SLOs To Tame the AI Platform Chaos - Alexa Griffith & Ankita Chaudhari [Kubecon EU]
2024
- Keynote: Centralizing & Simplifying Enterprise AI Workflows with Envoy AI Gateway [Kubecon NA]
- The Hitchhiker’s Guide to Kubernetes Platforms: Don’t Panic, Just Launch! [Kubecon EU AI Day]
2023
- Kubernetes Wonderland: Adventures in Platform Building [Kubecon China]
- Open Source Day Project: KServe [Grace Hopper]
- Red Light, Green Light: Traffic Security in the Service Mesh with Istio [Kubecon EU]
2022
2020
Technical Writing
All articles on Red Hat Developer
- Trace Kubernetes Resources for llm-d Model Serving [August 2026]
- Inside Red Hat AI Inference on EKS: Understanding the Kubernetes Resources [June 2026]
- A Reference Architecture for Adopters of Envoy AI Gateway [July 2025]
- Announcing KServe v0.15: Advancing Generative AI Model Serving [June 2025]
- Trend and Vibes for 2025 (MLOps newsletter feature) [January 2025]
- KServe Joins LF AI & Data as New Incubation Project [February 2022]
- Top Podcast Episodes 2021 [January 2022]
- A Lesson Learned on gRPC Client Side Load Balancing [ November 2021 ]
- Learnings from Building a Mission-Critical API [ July 2021 ]
- A Lesson Learned on Go's Context [ May 2021 ]
- Distributed Locking for Micro-Batch Processing: Preventing Resource Starvation [ Jan 2021 ]
- Deciding between Row- and Columnar-Stores | Why We Chose Both [ August 2020 ]
- How Data Is Stored: Down the Rabbit Hole [ July 2020 ]
- Airflow: how and when to use it (Advanced) [ May 2020 ]
- Airflow: how and when to use it [ May 2020 ]
- Using Google Cloud to Serve 10,000s of Personalized Recs Per Second [ May 2020 ]
- Making Airflow Pods Use a Private Google Cloud SQL Connection [ April 2020 ]
- Kubernetes Pod Logging in the Airflow UI [ December 2019 ]
- Using Radix in Golang: Creating & Testing a Redis Client [ October 2019 ]
Publications
Contact
- alexa.nicole.griffith@gmail.com