Stan Kirdey
San Francisco, California, United States
Summary
👤
SeniorStan Kirdey is a seasoned software engineer and technical leader with a decade of AI/ML-focused experience at Netflix, Amazon, and multiple stealth and startup ventures in Silicon Valley. As a Member Of Technical Staff at Stealth AI Startup, he combines hands-on backend engineering with strategic product direction. His open-source contributions include backend work on the Haystack AI orchestration framework, adding an in-memory document store, tagging filters, and tests that improve document metadata handling and retrieval. Previously at Netflix, he led machine learning platform and observability efforts, shaping scalable ML systems. Founding and CTO roles at Amplifier Health focused on large audio transformers for voice diagnostics and multi-agent LLM workflows in healthcare, reflecting a rare blend of AI research and practical deployment. Based in San Jose, California, he fosters collaborative culture and continuous learning, mentoring engineers and teaching applied AI part-time.
11 years of coding experience
Stackoverflow
611reputation
196kreached
28answers
5questions
Github Skills (19)
python10
large-language-model10
machine-learning10
large-language-models10
retrieval-augmented-generation10
nlp10
testing9
language-model8
ai8
language-models8
pytorch8
npm-install6
package-lock-json6
webapp26
spring-security6
Programming languages (14)
Github contributions (5)
deepset-ai/haystack
Apr 2020 - Jun 2020
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:8 commits, 12 PRs, 14 comments in 1 month
Contributions summary:Stan primarily contributed to the backend functionality of the Haystack framework. Their commits focused on implementing an in-memory document store, adding filtering by tags and embedding queries. They also added unit tests, coverage reports, and fixed a typo within the transformer reader module. Furthermore, they contributed to the TF-IDF retriever and transformer reader by adding features related to document meta data.
pythonbertfinetuningproduction-readyhuggingface-transformers
skirdey/vocode-python
Jul 2023 - Feb 2024
🤖 Build voice-based LLM agents. Modular + open source.
Contributions:73 pushes, 10 branches in 6 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.