← Back to home

Speaking

Talks on AI platforms, agent evaluation, and the infrastructure behind production AI.

Browse recordings

Talk archive

2026

AI Performance Engineering Meetup 2026

From Agent Traces to Agent Training: Closing the Continuous Learning Loop

Watch the recording

AWS Community Day Bay Area 2026

From Agent Traces to Agent Simulations: Closing the AgentOps Loop on AWS

Watch the talk

AI Engineer World's Fair 2026

From Agent Traces to Agent Simulations: The Next Era of Agent Evaluation

Watch the talk

AI DevSummit 2026

Building Scalable End-to-End Deep Learning Pipelines in the Cloud

View session

AWS Community Day Security Edition 2026

Isolation vs Autonomy: Choosing Sandboxes for Terminal AI Agents

Watch the talk

2025

AWS Community Day 2025

Beyond Chat: Building Hybrid Agentic Workflows on AWS

View session

Embedded Vision Summit 2025

Scaling Machine Learning with Containers: Lessons Learned

View session

IPC APEX EXPO 2025

AI for Real: Improving Yield in SMA and Box Build

Watch the talk

2024

Re:Invent 2024

DEV317 | Scaling machine learning with containers on AWS: Lessons learned

Watch the talk

AWS Community Day Bay Area 2024

Leverage ML Inference for Generative AI Models on AWS

View session

PlatformCon 2024

Building scalable end-to-end deep learning pipelines in the cloud

View session

Embedded Vision Summit 2024

Testing Cloud-to-Edge Deep Learning Pipelines: Ensuring Robustness and Efficiency

View session

AWS in Russian Podcast · 2024

LLM (generative AI) on AWS

View session

Mongo DB TV · 2024

AWS and Generative AI - Services, Deployments and RAG with Bedrock

View session

DeveloperWeek 2024

Building Scalable End-to-End Deep Learning Pipelines in the Cloud

View session

2023

Re:Invent 2023 Mongo DB lighting talk

Gen AI Deployment on AWS: A Deep Dive into services and options

View session

AWS ML Heroes in 15 · 2023

Leverage ML Inference for Generative AI Models on AWS

View session

AWS ML Heroes in 15 · 2023

Harnessing Low-code/No-Code Machine Learning on AWS

View session

Embedded Vision Summit 2023

A Survey of Model Compression Methods

View session

2022

AWS Summit San Francisco 2022

Building scalable end-to-end deep learning pipelines in the cloud

View session

AWS Summit San Francisco 2022

Build scalable machine learning pipelines on AWS

View session

Global AI Virtual Conference 2022

Building scalable end-to-end deep learning pipelines in the cloud

View session

Build Better 2022

Instrumental Data Correlations: Solving Unsolvable Problems

View session

ASPLOS 2022

Turbocharging Serverless Research with vHive

View session

2021

AI DevWorld 2021

Serverless for Machine Learning Pipelines

View session

DataOps Summit 2021

Building Scalable End-to-End Deep Learning Pipelines in the Cloud

View session

DataCon LA 2021

Building Scalable End-to-End Deep Learning Pipelines in the Cloud

View session

DataTalks.Club 2021

Building Scalable End-to-End Deep Learning Pipelines in the Cloud

View session

MLOps: Production & Engineering Bay Area 2021

Serverless for Machine Learning Pipelines

View session

2020

AWS Community Day 2020

Building Scalable End-to-End Deep Learning Pipeline in the Cloud

View session

AI DevWorld 2020

Building Scalable End-to-End Deep Learning Pipeline in the Cloud

View session

Data Con LA 2020

Tips for Writing an Effective AI and Deep Learning Book

Watch the talk

O'Reilly Live Online Training · 2020

First Steps AWS Serverless for Deep Learning Applications

View session

DevOps World 2020

Building Scalable End-to-End Deep Learning Pipeline in the Cloud

View session

Cloud Native Revolution 2020

Serverless for AI applications

View session

AWS Machine Learning Zero-to-Hero · 2020

AWS Step Functions + Amazon SageMaker/AWS Batch/AWS Fargate to Organize Deep learning Pipelines

View session

ServerlessDays Virtual 2020

Serverless for AI applications

View session

O'Reilly Live Online Training · 2020

First Steps AWS Serverless for Deep Learning Applications

View session

Developerweek Global 2020

Building Scalable End-To-End Deep Learning Pipeline in the Cloud

View session

2019

Global Big Data Conference 2019

Serverless architecture for AI applications

View session

O'Reilly Software Architecture 2019

Serverless architecture for data science

View session

O'Reilly Velocity 2019

Serverless architecture for data science

View session

O'Reilly Velocity 2019

Serverless workflows for orchestration hybrid cluster-based and serverless processing

View session

2018

O'Reilly OSCON 2018

Serverless deep learning; or, How to port your TensorFlow model to AWS Lambda

View session

AI With the Best 2018

Serverless Deployment of Deep Learning Models

View session

Developer Week 2018

Serverless Tensorflow and How to Port Your Model Using It

View session

2017

Scale By The Bay 2017

Serverless Tensorflow 1.0.0 on AWS. Wait what?

View session

State Of The Map US 2017

Detect missing buildings using imagery

View session

2014

SPIE Electronic Imaging 2014

Image processing for drawing recognition

View session

Recordings

Faster AI: GPU Rooflines and Continuous Agent Learning
Rustem Feyzkhanov (Snorkel AI): From Agent Traces to Agent Simulations, full talk
From Agent Traces to Agent Simulations — Rustem Feyzkhanov, Snorkel AI
Isolation vs Autonomy: Choosing Sandboxes for Terminal AI Agents [Advanced] - Rustem Feyzkhanov
"Scaling Machine Learning with Containers: Lessons Learned," a Presentation from Instrumental
AI for Real: Improving Yield in SMA and Box Build.
AWS re:Invent 2024 - Scaling machine learning with containers on AWS: Lessons learned (DEV317)
Rustem Feyzkhanov - Leverage ML Inference for Generative AI Models on AWS
Instrumental Discusses Testing Deep Learning Pipelines to Ensure Robustness and Efficiency (Preview)
Building scalable end-to-end deep learning pipelines in the cloud - Rustem Feyzkhanov
AWS and Generative AI - Services, Deployments and RAG with Bedrock
Leveraging ML Inference for Generative AI on AWS - AWS ML Heroes in 15
AWS ML Heroes in 15: Harnessing Low-code/No-Code Machine Learning on AWS
"A Survey of Model Compression Methods," a Presentation from Instrumental
Instrumental's Rustem Feyzkhanov Shares a Survey of Model Compression Methods (Preview)
ACD22-1-04 Build scalable end-to-end deep learning pipelines in the cloud - Rustem Feyzkhanov
Data Con LA 2021 - Building scalable end-to-end deep learning pipelines in the cloud
Introduction to serverless programming with AWS Lambda 2/8
Building Scalable End-to-End Deep Learning Pipelines in the Cloud - Rustem Feyzkhanov
Building Scalable End-To-End Deep Learning Pipelines In The Cloud
Panel - Tips for Writing an Effective AI and Deep Learning Book
ServerlessDays Virtual - July 2020
Building Scalable End-To-End Deep Learning Pipeline in the Cloud (DeveloperWeek Global 2020)
Serverless architecture for data science | O'Reilly Velocity 2019 | Rustem Feyzkhanov
Serverless architecture for data science | O'Reilly Software Architecture 2019 | Rustem Feyzkhanov
Strata SF 2019 | Serverless workflows for hybrid cluster/serverless processing | Rustem Feyzkhanov
OSCON 2018 | Serverless deep learning | Rustem Feyzkhanov
scale.bythebay.io: Rustem Feyzkhanov, Serverless Tensorflow 1.0.0 on AWS. Wait what?
Detect missing buildings using imagery

Get in touch about speaking