- Email: alexander.kedrik@gmail.com
- LinkedIn: alex-kedryk
- GitHub: alkedr
TL;DR: An experienced software engineer looking for ways to make a positive impact on AI safety.
- Replicated a part of the "Alignment Faking in LLMs" paper and published a LessWrong post about it.
Sept 2025 – present
7 months
- Built or significantly improved several internal tools for running LLM evals.
Apr 2024 – Aug 2025
1 year 5 months
-
Sped up model checkpoint uploading during training 2x to make it possible to make checkpoints more often and lose less progress after failures.
-
Wrote a tool for benchmarking different methods of checkpoint uploading.
Sept 2023 – Apr 2024
8 months
-
Designed and implemented infrastructure for a real-time video processing pipeline for tracking player movements on a football field. Python, PostgreSQL, a message queue similar to Kafka, FFmpeg.
-
Wrote a tool for visualizing the progress of each video chunk in real-time.
Nov 2022 – Sept 2023
11 months
-
Sped up video 3D reconstruction pipeline 4x by finding and fixing infrastructural issues and profiling with Torch profiler.
-
Researched and tested alternatives to the differentiable 3D-renderer that we were using. Nvdiffrast, Mitsuba 3, Pytorch3d.
-
Wrote a tool for converting reconstructed animated 3D model back into video for easy viewing.
May 2020 – Nov 2022
2 years 7 months
-
Designed and implemented a task queue service for launching simulator tests that could scale to thousands of workers. Python, PostgreSQL.
-
Designed, prototyped, and helped implement an inference server cluster that could handle over 12k RPS and tens of GBit/s of incoming traffic. Python, C++, Nvidia Triton Inference Server.
June 2017 – May 2020
3 years
- Worked on a CI/CD web service and a log parsing service. Java, MongoDB.
Aug 2013 – June 2017
3 years 11 months
Saint-Petersburg National Research University of Information Technologies, Mechanics and Optics (ITMO), Computer Science
BS
Sept 2011 – June 2015
Technologies: Python, C++, PyTorch, Jupyter, Cursor