Bora Tunca
Software Engineer at Bloomberg
New York, New York, United States
Summary
👤
Senior🎓
Top SchoolBora Tunca is a software engineer with 11 years of experience building reliable, well-monitored production systems and shipping scalable infrastructure for AI and consumer products. Currently at Bloomberg’s AI Group, he focuses on productionizing large language models and previously helped build Meta’s next-generation inference platform for multi-model, multi-modal workloads. His background spans microservices, payments, and data center tooling from roles at SoundCloud and Facebook, and early full-stack work in fintech and web portals. An active contributor to KServe, he extended its serverless ML inference capabilities with OpenAI model support—demonstrating a blend of practical systems engineering and ML-serving expertise. Known for favoring tested code and observability, he pairs hands-on implementation with a focus on operational reliability. Based in New York, he brings cross-functional leadership experience and a pragmatic approach to moving models from prototype to production.
11 years of coding experience
12 years of employment as a software developer
BSc Computer Science, BSc Computer Science at Ege University
Github Skills (9)
kubernetes10
machine-learning10
model-management10
openai10
python10
kubernetes-pods10
kss10
tensorflow7
pytorch7
Programming languages (7)
Github contributions (5)
kserve/kserve
Dec 2023 - Jun 2024
Standardized Serverless ML Inference Platform on Kubernetes
Role in this project:
ML Engineer
ML EngineerContributions:21 reviews, 5 PRs, 47 comments in 5 months
Contributions summary:Bora primarily contributed to the implementation of OpenAI model support within the KServe framework. This included adding new model types, integrating OpenAI's API, and ensuring compatibility with the existing model repository and serving infrastructure. They also addressed various code formatting and type-related issues, while also adding logging improvements and code refactoring. Their work focuses on extending KServe's capabilities to support different models, with a strong emphasis on serving large language models.
xgboostsklearnserverlessclient-goknative
grandbora/prometheus
Aug 2016 - Nov 2017
The Prometheus monitoring system and time series database.
Contributions:63 pushes, 34 branches, 3 comments in 1 year 3 months
time-series-databaseprometheus-exporterseries-databasedatabaseprometheus-monitoring
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.