About

About Pete

I work on making language models reliable—through research, engineering, and writing about what works.

Pete's profile picture
Bangkok

Research Scientist @ Typhoon

Hi, I'm Pittawat (Pete).

I’m interested in shaping model behavior to align with human preferences, domain-specific requirements, task objectives, and cultural values. I’m currently exploring approaches including context engineering, prompt engineering, and post-training (SFT/RFT).

LinkedIn GitHub Google Scholar
Right now
  • Conducting frontier research in LLM Reasoning and Post-training (SFT/RFT).
  • Investigating LLM Inference: context engineering, test-time scaling, and agents.
  • Leading external research collaborations with academic and industrial partners.
  • Bridging research and engineering to translate findings into robust PoCs.
Snapshot

Current role

Research Scientist @ Typhoon

Conducting frontier research in LLM Reasoning and Post-training (SFT/RFT).

Approach

Research to production

Bridging the gap between research, engineering, and model adoption.

Based in

Bangkok

Remote-friendly

What drives my work

Four themes that connect the research, tools, and writing.

Behavior Shaping

Exploring approaches to align model behavior with human preferences and domain requirements, including context engineering, prompt engineering, and post-training (SFT/RFT).

Reasoning Models

Developing open reasoning models like Typhoon T1 and investigating medical reasoning models (MRMs) with novel alignment techniques.

Evaluation & Safety

Understanding and mitigating biases and risks. Building evaluation frameworks like BenchING to test structured output following.

Applied AI

Showcasing real-world applications (Typhoon Application Week) and collaborating on projects in healthcare and gaming.

Background

How I got here and what I'm doing now.

I’m interested in shaping model behavior to align with human preferences, domain-specific requirements (e.g., games and medical), task objectives, and cultural values.

I’m currently exploring several approaches for behavior shaping, including context engineering, prompt engineering, and post-training (supervised fine-tuning and reinforcement fine-tuning).

I also care deeply about understanding and mitigating the biases and risks associated with modern AI models.

Timeline & milestones

Education, collaborations, and the work that shaped how I approach problems.

Spotlight milestones

  1. Oct 2024 – Present — Research Scientist, Typhoon team (SCB 10X R&D)

    Conducting frontier research in LLM Reasoning and Post-training (SFT/RFT). Spearheading Typhoon T1 and external collaborations.

  2. Sep 2024 — M.Eng., Ritsumeikan University (Valedictorian)

    Valedictorian (4.93/5.00). Thesis on Null-Shot Prompting and Hallucination in LLMs.

  3. 2022 — Research Associate (IC2, SIT KMUTT)

    Led end‑to‑end ML/AR/web projects; presented Krathu‑500; hosted Kaggle competition.

  4. 2022 — B.Sc. (Computer Science), King Mongkut's University of Technology Thonburi (First Class Honour)

    First-Class Honors (3.99/4.00). Senior project on Automatic Mind Map Generation.

  5. 2019–2020 — Siriraj Hospital

    React Native developer; added features and data collection flows.

Education

M.Eng., Intelligent Computer Entertainment Lab, Ritsumeikan University

2022 — 2024

GPA: 4.93/5.00, Valedictorian. Thesis: Null-Shot Prompting: Rethinking Prompting Large Language Models With Hallucination.

B.Sc. Computer Science, KMUTT (First-class honours)

2018 — 2022

GPA: 3.99/4.00. Senior project: COEUS: Automatic English Mind Map Generation From Text.

Collaborations & community

Research Collaborations

Spearheading external collaborations with top academic and industrial partners (VISTEC, SiData, SCBX).

  • Investigating prior prompt engineering and inference-time strategies.
  • Leading research on medical reasoning models and conversational agents.

Leadership & Outreach

Cultivating technical communities and bridging the gap between frontier research and application.

  • Lead, Google Developer Group on Campus (GDGoC) at KMUTT.
  • Partnering with DevRel to disseminate research findings via technical blogs and talks.

Service & learning rituals

  • Lead Developer, KMUTT COVID-19 Donation Management Platform.
  • Organized Junior Webmaster Camp 8, Junior Programmer Camp XV, and SIT Code 2019.
  • Actively engaging with the technical community through public speaking and blogging.
  • Mentoring research interns and guiding projects from ideation to publication.
Read the extended timeline

  1. 2025 — Typhoon Application Week

    Built and shipped 7+ LLM-powered apps.

  2. 2025 — Typhoon T1 (research preview)

    The first Southeast Asia reasoning model.

  3. Oct 2024 – Present — Research Scientist, Typhoon team (SCB 10X R&D)

    Conducting frontier research in LLM Reasoning and Post-training (SFT/RFT). Spearheading Typhoon T1 and external collaborations.

  4. Sep 2024 — M.Eng., Ritsumeikan University (Valedictorian)

    Valedictorian (4.93/5.00). Thesis on Null-Shot Prompting and Hallucination in LLMs.

  5. 2022 — Ethical Hacking Workshop

    5‑day red‑team training by NIA & NBTC.

  6. 2022 — Research Associate (IC2, SIT KMUTT)

    Led end‑to‑end ML/AR/web projects; presented Krathu‑500; hosted Kaggle competition.

  7. 2022 — B.Sc. (Computer Science), King Mongkut's University of Technology Thonburi (First Class Honour)

    First-Class Honors (3.99/4.00). Senior project on Automatic Mind Map Generation.

  8. 2021 — LINE Thailand Internship

    Full‑stack work on LINE Shopping; Vue 2→3 migration; microservices.

  9. 2020–2021 — Siriraj Hospital (Mahidol)

    Tech lead & Flutter dev; React Native→Flutter migration; app size/load wins.

  10. 2020 — COVID‑19 Support Platform (KMUTT)

    Led 10‑person team; 300+ shipments tracked; 50+ hospitals served.

  11. 2020 — Huawei ICT APAC (Network Track)

    Participated in regional competition; routing/switching focus.

  12. 2019–2020 — Siriraj Hospital

    React Native developer; added features and data collection flows.

  13. 2019 — Young Webmaster Camp 17th

    Selected (programming major); built MVP for social impact.

  14. 2019 — Google Tech Challenge (Bangkok)

    Selected team; coding + non‑coding puzzles.