Peerapon Wechsuwanmanee

• Spearheaded the multi-agent AI system that won the company Hackathon 2025 ('Technology Love' category, among hundreds of developers), auto-resolving common software-development issues by surfacing internal documentation and REWE-specific infrastructure fixes - targeting the ~5% of weekly developer time lost to manual lookups and cross-team queries.
• Architected a multi-agent extension to the store-employee chatbot - natural-language task creation via an MCP tool over a Google ADK agent-to-agent architecture - placing 3rd at Google Agent Factory 2026.
• Owned end-to-end delivery of 4 Generative AI products, from architecture to production, for back-office and in-market use cases - serving thousands of German retail markets and delivering directly to business and operational teams.
• Designed the foundational scalable, observable GenAI/ML architecture with production-grade deployment and monitoring.
• Led design and delivery of a few-shot RAG service (LangChain, Qdrant, FastAPI, Snowflake) auto-generating personalized coupon copy from aggregated master-data offers - replacing manual weekly copywriting after migration off a third-party loyalty platform, with human-in-the-loop corrections feeding curated examples into later generations.
• Designed and built a multi-agent GenAI system (FastAPI, Snowflake, pgvector) mapping weekly on-sale items to seasonally-relevant recipes (Easter, Christmas, summer BBQ) with explainable reasoning for marketing materials, eliminating hours of manual item-to-recipe matching per week.
• Led productionization of a hybrid keyword/semantic, multi-modal internal-document search engine for REWE's nationwide store network - owned the system and architecture design, vector-database evaluation, and decoupled data-loading services - replacing a third-party keyword search and cutting employee document lookup from hours to under 5 minutes.
• Architected an agent-to-agent (A2A) orchestrator chatbot (Google ADK, MCP, Kubernetes, LangSmith) routing market-employee queries to specialized agents (semantic document search, task-system reader) as a one-stop in-market assistant - in development, with rollout planned to thousands of German markets by end of 2026.
• Advanced agentic engineering adoption about spec-driven-development beyond the immediate team through best-practice sessions reaching nearly a thousand internal developers across Europe
• Co-founded the Machine Learning Guild - a growing cross-team community of 10-20 ML practitioners driving MLOps best-practice adoption through regular talks and hands-on sessions - standardizing ML workflows, speeding new-engineer ramp-up, and promoting cross-team reuse of accelerators over rebuilding.

• Integrated a legacy high-performance database engine into the Apache Spark ecosystem, developing Scala integration components.

• Built a reusable AWS MLOps accelerator - Terraform-provisioned SageMaker training and inference templates with MLflow tracking - to cut time-to-PoC on recurring components across client engagements.
• Instantiated the accelerator for LLM-based PDF document summarization (LangChain), delivering an end-to-end training-to-serving pipeline.
• Instantiated the accelerator for PyTorch computer-vision defect detection on steel-surface production lines, classifying surface anomalies from line imagery.
• Engineered an end-to-end PySpark predictive-maintenance pipeline for the automotive sector - data extraction through feature engineering to a Streamlit decisioning dashboard - directly enabling the client's maintenance-cost reduction.
• Spearheaded extension and optimization of a complex Scala/Spark ETL pipeline for automotive IoT analysis, processing terabytes of sensor data with improved throughput and reliability.
• Delivered a long-stalled ETL project 2x ahead of estimate by implementing the missing domain equations and re-optimizing the data-processing workflow.

• Led a 4-5 person Speech-to-Text product team building speaker diarization, speaker recognition, and speech recognition models.
• Built end-to-end ASR pipeline (data acquisition → fine-tuning → deployment) reaching 8% Character Error Rate on the in-domain Thai test set versus 11% for Google Speech Recognition - outperforming the incumbent on a low-resource language in target domains.

• Drove multiscale, scale-bridging finite-element modelling of damage and formability in advanced high-strength and multiphase (dual-phase) steels - coupling micromechanical ABAQUS simulation (ABAQUS Python API) with experimental material characterization.
• Authored 9 peer-reviewed journal and conference papers (2014-2021) spanning surface-roughness effects on cold formability, hybrid damage mechanics, hole-expansion and edge-crack sensitivity of multiphase steels, and micromechanical plasticity-and-damage initiation (NUMIFORM, IDDRG, Materials & Design, Computational Materials Science).
• Developed multi-scale FE tools and multi-objective optimization for abrasion- and wear-resistant steels within an EU-funded (RFCS, European Commission) consortium spanning universities and industry partners.
• Applied machine learning (SVR, ANN, LSTM) to predict ferritic-steel flow curves - treating stress-strain response as time-series data to extend computational mechanics into data-driven materials modelling.
• Coordinated international, cross-institution research projects and owned the MATLAB/Python/ABAQUS simulation toolchain underpinning the institute's damage-modelling work.

• Built Python-driven algorithmic Computer-Aided Engineering (CAE) 2D/3D models for multi-phase steel microstructure representation in ABAQUS as a foundation for follow-on research activities - work contributed to 2 peer-reviewed journal publications.

• Developed an automation workflow for multi-body simulation of an electrical drive in MD ADAMS.
• Built thermal network models for the window-lift and wiper drives in ABAQUS.
• Automated the optimization workflow for both projects with optiSLang.

Personal Portfolio & Automated CV Generator

• Built and deployed a personal portfolio and blog as a fully static Astro site with React interactive islands, Tailwind CSS, and TypeScript, shipped to Cloudflare Pages.
• Architected a single shared JSON data contract - extracted from a YAML skeleton - that drives both the homepage and an automated Typst-based CV generator, keeping all content in sync across outputs.
• Added an MDX-driven blog with RSS feed and auto-generated sitemap, build-time image optimization, and a Vitest + Testing Library suite.

Semantic Product Search Engine

• Researched and evaluated search engine options for a second-hand e-commerce platform, selecting Meilisearch for its hybrid semantic/lexical search, bilingual Thai/English support, and cost profile at scale - saving months of in-house search development.
• Designed and deployed a real-time PostgreSQL → Meilisearch sync pipeline using logical replication and MeiliBridge, enabling sub-second product index updates without changes to the host application.
• Tuned search relevance through ranking rules, typo tolerance, embeddings, and query strategies (type-ahead, faceted filtering, brand relaxation) ahead of launch.
• Contributed compatibility patches to the open-source MeiliBridge Rust codebase to unblock production adoption.

Motorbike Condition Evaluation

• Built a multi-modal ML regression pipeline fusing 39-dimensional MFCC audio features (extracted from inspection videos via librosa), Thai-language BERT embeddings (WangchanBERTa), and categorical inspection inputs to predict a 0-100 motorcycle condition score.
• Benchmarked 5 regression algorithms (ElasticNet, Random Forest, Gradient Boosting, SVR, XGBoost) with scikit-learn RandomizedSearchCV hyperparameter tuning; serialized the best-performing pipeline for cloud-hosted inference.
• Engineered an audio feature extraction pipeline that converts MP4 inspection videos to log-mel spectrograms, computes MFCC + delta + delta-delta coefficients, and normalizes across axes to produce a stable 39-feature vector.
• Deployed a production FastAPI + Streamlit application with object-storage video storage, PostgreSQL result logging, and Docker — submitting a video returns a scored risk assessment in real time.

Credit Risk Assessment

• Performed exploratory analysis and built a reproducible data-cleaning and transformation pipeline on a raw credit dataset.
• Ran model selection across candidate classifiers with per-segment personalized feature selection to sharpen credit-default discrimination.
• Delivered an interactive Streamlit decisioning UI to score applicants and inspect the drivers behind each prediction.

Credit Default Prediction

• Built a full-lifecycle credit-default MLOps system: EDA, automated data-cleaning pipeline, MLflow experiment tracking, blue-green model selection, and Prefect-orchestrated automatic retraining.
• Ran a profit-optimized threshold simulation achieving a 30% profit increase on out-of-sample data versus a baseline cut-off policy.
• Deployed a production-grade, scalable FastAPI inference service serving real-time default predictions, with retraining triggered automatically as new repayment data arrived.

Customer Feedback Classification

• Reduced case resolution time by 18% by building an automated Thai-language text classifier that routes incoming feedback to the correct service team.
• Implemented a RAG pipeline using OpenAI embeddings and ChromaDB to retrieve similar labeled examples as few-shot context, improving classification accuracy without retraining.
• Packaged the system as a Dockerized FastAPI service, enabling new training examples to be added at runtime via CSV upload without redeployment.

Automotive License Plate Recognition

• Built a MATLAB computer-vision system that reads automotive license plates, developing the recognition pipeline almost from scratch in the era before deep-learning frameworks were available.

Built a multi-agent extension to REWE's centralized store-employee chatbot enabling natural-language task creation via a FastMCP MCP tool, on a decoupled Google ADK agent-to-agent (A2A) architecture.

Multi-agent AI system auto-resolving common software-development issues - surfacing internal docs and REWE-specific infrastructure fixes.

Built real-time anomaly detection deep learning model for predictive maintenance of electrical drives.

Built ML algorithms to investigate microstructure, fracture toughness, and early-stage fatigue of steels in nuclear power plant from non-destructive evaluation (NDE) measurements. Collaborated with international teammates in agile environment.

Built NLP model predicting product ratings in English from Malaysian/Indonesian e-commerce sites (top 5%), and computer vision model for 42-class product image classification.

Improved predictive maintenance accuracy from turbocharger inspection data.

Built ML model to predict success rate of part extraction from laser machine given geometry features and machine parameters.

Mechanical design and manufacturing engineer on Team Skuba, Kasetsart University's interdisciplinary autonomous-robot-soccer team, at the international RoboCup Small Size League.

Influence of surface roughness on cold formability in bending processes: a multiscale modelling approach with the hybrid damage mechanics model

International Journal of Material Forming, 14(6) (2021)Source

Numerical Evaluation of Surface Roughness Influences on Cold Formability of DP Steel

13th Intl. Conf. Numerical Methods in Industrial Forming Processes (NUMIFORM) (2019)Source

Modeling the Surface Roughness Influence on the Hole Expansion Ratio of Multiphase Steel

38th Intl. Deep Drawing Research Group (IDDRG) Annual Conference (2019)Source

Scalebridging Approaches to Assess the Edge Crack Sensitivity of Multiphase Steels

13th Intl. Conf. Numerical Methods in Industrial Forming Processes (NUMIFORM) (2019)

A Numerical Approach to Evaluate Roughness Effects on Localization and Damage in Sheet Materials

37th Intl. Deep Drawing Research Group (IDDRG) Annual Conference (2018)Source

Finite Element Model in Abrasion Analysis for Single-Asperity Scratch Test

Fracture Fatigue and Wear, Springer (2018)Source

Multi-objective Optimization of Multi-scale Finite Element Analysis for Wear Resistant Steel

U.S. National Congress on Computational Mechanics (2017)

Prediction of Plasticity and Damage Initiation Behaviour of C45E+N Steel by Micromechanical Modelling

Materials and Design (2017)Source

The Modelling Scheme to Evaluate the Influence of Microstructure Features on Microcrack Formation of DP-steel

Computational Materials Science (2014)Source

Development of the Modified Kinematics for a Wheeled Mobile Robot

Intl. Technical Conf. Circuits/Systems, Computers and Communications (2010)

Kinematics Simulation by using MSC.ADAMS for a 6-DOF Industrial Robot Arm

Thailand Simulation and Modeling Conference (2010)

• Designed and taught a weekend cohort of ~40 IT and non-IT professionals end-to-end AI product development, from model to deployed service.
• Topics: Python, Machine Learning, FastAPI, LLM API, Streamlit, Docker, Linux, AWS.

• Led a weekend cohort of ~100 data enthusiasts into data-engineering careers through lectures and hands-on workshops.
• Topics: Basic Data Engineering, Python, SQL, AWS, Git, Workflow Orchestration.
• Prepared and managed AWS cloud infrastructure for data engineering, data science, and data analytics sections.

• Organized and hosted the meetup at the Data Reply Munich office, inviting Seldon as a guest speaker.
• Presented talk on 'Big Pictures and Use-cases in Predictive Maintenance'.
• Published recap article on Medium (DataReply publication).

• Provided free digital education for locals, newcomers, and refugees in Munich.
• Supervised and guided students for their final projects.

• Established the Thai language team and led localization of 2 out of 9 chapters of the HuggingFace NLP course.

• Provided hands-on lectures to 450 online students - Intro to Python, NumPy/Pandas, Feature Engineering, Model Deployment.
• Supervised students' end-to-end Computer Vision, NLP, and Time-Series Analysis projects.

• Provided weekly supervision and consultancy on data science projects for career switchers.
• Donated all compensation to charitable institutions (UNICEF, Wikimedia, ProVeg).

Predicted mechanical response (stress-strain) of ferritic steel at different conditions using SVR, ANN, and LSTM. Treated stress-strain curves as time-series data.

Developed multi-scale computational tools for abrasion in agricultural steel. EU-funded collaboration (RFCS, European Commission) across universities and industry.

Studied and implemented adaptive control scheme for medical devices and industrial machines.

Analyzed and synthesized optimized lumped-mass model workflow for delta robot elasticity reduction.

Simulated kinematics of 6-DOF industrial robot arm.