Update I am on the industry job market! I am looking for research or software engineering positions on program synthesis, program repair, LLM code generation, intelligent coding assistants etc. to start October 2024.

About Me

I am a PhD candidate in the Computer Science & Engineering (CSE) department at UC San Diego, where I conduct research in Programming Languages with my advisor Prof. Ranjit Jhala. My current research focuses on developing tools that make software development, programming, and debugging easier. Specifically, I work on Automated Program Repair and Synthesis, aiming to create fast and reliable tools by combining traditional Programming Languages (PL) research with state-of-the-art Machine Learning (ML) techniques.

Previously, I did my undergraduate studies on Electrical and Computer Engineering at National Technical University of Athens, where I also worked on my thesis on “Resumption Monad Transformers and their Applications in the Semantics of Concurrency” under the supervision of Prof. Nikolaos Papaspyrou.

My name is Georgios or Yiorgos (Greek: Γεώργιος or Γιώργος) but you can also call me George. I grew up in Kalamata, a sleepy beach town in Greece. In my free time, I enjoy playing basketball or going out with friends. I also occasionally do some oil painting and drawing.

Work & Research Experience

A comprehensive list of my work and research experience is available in my most recent resume: Georgios Sakkas’ CV

UC San Diego (U.S.A., Sep. 2018 - Present)

• PhD Candidate at the Programming Systems group – Advisor: Prof. Ranjit Jhala
• Focus: Neurosymbolic Program Repair using Programming Languages & Machine Learning research, including Formal Methods, Static Analysis, Neural Networks & LLMs

Microsoft Research (Redmond, WA, U.S.A., Jun. 2022 - Sep. 2022)

• Research Intern at the Research in Software Engineering (RiSE) group working with Shuvendu Lahiri
• Publication on interactive code generation via test-driven user intent formalization, using program synthesis, static analysis, and state-of-the-art LLMs (Codex, InCoder, CodeGen etc.)

Amazon.com (San Francisco, CA, U.S.A., Jun. 2021 - Sep. 2021)

• Applied Scientist Intern at the CodeGuru Reviewer team of the Automated Reasoning group
• Extended a taint-analysis tool’s data-flow operations to capture constraints and add path sensitivity to the analysis

Bloomberg L.P. (New York, NY, U.S.A., Jun. 2020 - Aug. 2020)

• Software Engineer Intern at the Static Analysis & Automated Refactoring team of the Developer Experience group
• Implemented a new automated control-flow refactoring tool for legacy Fortran code

National Technical University of Athens (Greece, Nov. 2016 - Jul. 2018)

• Research Assistant at the Software Engineering Lab (Softlab) — Supervisor: Associate Prof. Nikolaos Papaspyrou
• Thesis: Resumption Monad Transformers and their Applications in the Semantics of Concurrency

Rutgers, The State University of New Jersey (U.S.A., Jul. 2016 - Aug. 2016)

• Visiting Research Student at the ParaMathics group — Supervisor: Assistant Prof. Maryam Dehnavi
• Worked on Cache Oblivious Algorithms, High Performance Computing, Parallel Computing, Testing in HPCs (XSEDE, Stampede)

Publications

My most recent publications include:

1. Title omitted for double-blind review

• Georgios Sakkas, Pratyush Sahu, Kyeling Ong, Ranjit Jhala
• Work on LLMs and Program Verification
• Submitted to ICSE 2025

2. Exploring the Effectiveness of LLM based Test-driven Interactive Code Generation: User Study and Empirical Evaluation

• Sarah Fakhoury*, Aaditya Naik*, Georgios Sakkas*, Saikat Chakraborty, Madan Musuvathi, Shuvendu K Lahiri (*equal contribution)
• International Conference on Software Engineering: Companion Proceedings (ICSE) 2024 [Paper]

3. Seq2Parse: Neurosymbolic Parse Error Repair

• Georgios Sakkas, Madeline Endres, Philip J. Guo, Westley Weimer, Ranjit Jhala
• Proceedings of the ACM on Programming Languages 6, Article 167 (OOPSLA) 2022 [Paper] [Code]

4. Interactive Code Generation via Test-Driven User-Intent Formalization

• Shuvendu K Lahiri*, Aaditya Naik*, Georgios Sakkas*, Piali Choudhury, Curtis von Veh, Madanlal Musuvathi, Jeevana Priya Inala, Chenglong Wang, Jianfeng Gao (*equal contribution)
• arXiv preprint Aug. 2022 [Paper]

5. Type Error Feedback via Analytic Program Repair

• Georgios Sakkas, Madeline Endres, Benjamin Cosman, Westley Weimer, Ranjit Jhala
• Programming Languages Design and Implementation (PLDI) 2020 [Paper] [Code]

6. PABLO: Helping Novices Debug Python Code Through Data-Driven Fault Localization

• Benjamin Cosman, Madeline Endres, Georgios Sakkas, Leon Medvinsky, Yao-Yuan Yang, Ranjit Jhala, Kamalika Chaudhuri, Westley Weimer
• Special Interest Group on Computer Science Education (SIGCSE) Technical Symposium 2020 [Paper]

7. InFix: Automatically Repairing Novice Program Inputs

• Madeline Endres, Georgios Sakkas, Benjamin Cosman, Ranjit Jhala, Westley Weimer
• Automated Software Engineering (ASE) 2019. [Paper]

8. AIRMS: A Risk Management Tool using Machine Learning

• Spyros K. Chandrinos, Georgios Sakkas, Nikos D. Lagaros
• Journal of Expert Systems with Applications, Volume 105, 1 September 2018