Forward Deployed Engineer Training in Malaysia
Turn strong software engineers into FDEs — the client-facing engineers who scope, build and ship production AI agents inside real businesses. Hands-on with Google ADK, RAG and MCP, model-agnostic across Gemini, OpenAI and Claude.
What does an FDE actually do?Technical program for engineers with Python experience — not suitable for non-technical participants.
Workshop Dates
Our next public Forward Deployed Engineer intensive runs 11–13 November 2026. Register your interest, or book a private cohort for your team.
Public Training
November 11-13, 2026
Wednesday to Friday
Private Training
Custom Dates
Private Corporate Training
Looking to turn your entire engineering or data team into Forward Deployed Engineers?
Exclusive sessions available for groups of 25-35 pax per class. Fully HRDC claimable.
Companies We've Trained
Learning Outcomes
What You'll Be Able To Do
By the end of the 3-day intensive, you'll have the technical core of a Forward Deployed Engineer — not just theory.
Build production AI agents
Architect agents with Google ADK — Agent, Tool, Runner, Session — and swap between Gemini, OpenAI and Claude via LiteLLM without rewriting logic.
Design retrieval systems that actually work
Ingest real documents, choose chunking and embedding strategies, and measure retrieval quality instead of guessing.
Orchestrate multi-agent systems
Coordinate specialist agents with Sequential, Parallel and Loop patterns, and know when to use deterministic workflow vs. LLM-driven routing.
Connect agents to enterprise systems
Use MCP to wire agents into databases, REST APIs and internal tools — safely, with tool filtering and OAuth.
Evaluate agents like an engineer, not a demo
Build golden datasets, run LLM-as-judge evaluation, and catch regressions before a client does.
Ship with guardrails and observability
Add prompt-injection defences, PII redaction, cost tracking and Langfuse tracing before anything goes to production.
Deploy and version real systems
Containerise and deploy agents to Cloud Run and Vertex AI Agent Engine, with rollback and monitoring in place.
Defend your architecture like an FDE
Present a full multi-agent capstone build to peers and faculty — the same scrutiny a client-facing deployment gets.
8 Hands-On Labs
The production work of a Forward Deployed Engineer — build and deploy all 8 during the 3-day intensive.
Lab 1: Hello World Agent
Build a minimal agent and swap across Gemini, OpenAI, Claude via LiteLLM.
Lab 2: Multi-Tool Agent
Weather, budget, web-search tools with safety guardrail callbacks.
Lab 3: RAG-Augmented Agent
Ingest documents, build embeddings, wire retrieval into ADK agent, measure quality.
Lab 4: Multi-Agent Orchestration
Movie-pitch team with Sequential, Parallel, and LoopAgent patterns.
Lab 5: Dynamic Agent Routing
AgentTools, root agent routing, workflow vs LLM-driven comparison.
Lab 6: MCP & Enterprise Integration
MCP server, tool filtering, database querying with realistic data.
Lab 7: Eval, Observability & Guardrails
LLM-as-judge, Langfuse tracing, cost dashboard, guardrail callbacks.
Lab 8: Capstone Build & Deploy
Full multi-agent system deployed to Cloud Run.
The Stack You'll Use
Model-Agnostic, Production-Grade Tooling
Google ADK is the framework. Everything else is the same tooling a Forward Deployed Engineer runs in the field.
Google ADK
Agent framework
Agent, Tool, Runner and Session primitives — the architecture every lab in this course is built on.
Gemini
Model via API
Google's models, used natively inside ADK and benchmarked against OpenAI and Claude for cost and capability.
OpenAI
Model via API
Swapped in via LiteLLM to compare reasoning, latency and cost against the other providers, live.
Claude
Model via API
Anthropic's models for reasoning-heavy agents, plus the assistant many FDEs use to build and debug their own code.
LiteLLM
Model routing
One interface across every provider — swap Gemini, OpenAI, Claude or open-weight models without rewriting agent logic.
MCP
Model Context Protocol
The open standard for connecting agents to databases, APIs and enterprise tools with proper access control.
Langfuse
Observability & tracing
Trace every agent call, track token cost per request, and catch quality regressions before they ship.
Cloud Run & Vertex AI
Deployment
Ship your capstone agent to production with one command, then version, roll back and monitor it.
Forward Deployed Engineer Curriculum
A structured, hands-on 3-day, HRDC-claimable program that builds the technical core of a Forward Deployed Engineer.
Day 1: Agent Fundamentals, Tools & Retrieval (RAG)
The AI engineering paradigm shift, Google ADK architecture, and building your first production agents.
Core Theory
- AI Engineering Paradigm: AI Engineering vs Traditional Software — the paradigm shift, the observe-reason-act loop, and where agents deliver enterprise value.
- Google ADK & Model-Agnostic Design: ADK architecture: Agent, Tool, Runner, Session. Swap Gemini, OpenAI, Claude or open-weight models via LiteLLM. Live demo.
- RAG Architecture: Embeddings, chunking strategies, vector stores (Vertex AI, Chroma, pgvector). Hybrid search, re-ranking, retrieval evaluation.
- Prompt Engineering & Model Selection: System prompts, tool descriptions, output format constraints. Cost, latency and capability trade-offs across LLM providers.
Working Examples Built in Class
Build a minimal agent and swap it across Gemini, OpenAI, and Claude via LiteLLM to see model-agnostic design in action.
Weather, budget, and web-search tools with a before_model_callback safety guardrail blocking adversarial inputs.
Ingest a document corpus, build embeddings, wire a retrieval tool into an ADK agent, and measure retrieval quality.
Starter notebook stitching Labs 1, 2 & 4 — participants complete this before Day 1 to arrive ready to build.
Day 2: Multi-Agent Systems, Enterprise Integration & Model Customisation
Orchestrating multi-agent teams, connecting to enterprise systems via MCP, and understanding fine-tuning.
Core Theory
- Multi-Agent Orchestration: SequentialAgent, ParallelAgent, LoopAgent. Hierarchy, delegation, state sharing, and context passing between agents.
- MCP & Enterprise Integration: Model Context Protocol: connecting agents to databases, REST APIs via OpenAPI, and enterprise tools via OAuth + tool filtering.
- Model Customisation: Fine-Tuning, LoRA & MoE: The customisation ladder: prompting, RAG, LoRA/QLoRA, full fine-tuning. MoE models and the decision tree for when NOT to fine-tune.
- Agent-as-Tool & Dynamic Routing: Converting specialist agents into callable AgentTools. LLM-driven routing vs. deterministic workflow — when to use each.
Working Examples Built in Class
Movie-pitch team: Researcher, Writer, Critic. Build Sequential, then add Parallel critics and a LoopAgent revision cycle.
Convert specialists into AgentTools. Root agent dynamically routes queries. Compare workflow vs. LLM-driven routing.
Connect to an MCP server, implement tool filtering for safe access, query an external database with realistic data.
30-min concept-only session: LoRA, QLoRA, MoE architecture, and a decision framework for when NOT to fine-tune. No GPU needed.
Day 3: Production — Evaluation, Observability, Security & Deployment
Making agents production-ready with evaluation, tracing, guardrails, and Cloud Run deployment.
Core Theory
- Agent Evaluation & Testing: ADK evaluation framework, LLM-as-judge patterns, golden datasets, trajectory vs. response quality, and regression testing.
- Observability, Tracing & Cost Management: OpenTelemetry and Cloud Trace. Langfuse integration for tracing. Token and cost tracking per request. Latency budgets and quality alerts.
- Security, Guardrails & Responsible AI: Prompt injection defences, PII detection/redaction, tool-call authorisation, audit logging, and GDPR/EU AI Act compliance.
- Production Deployment: Containerise ADK agents. Deploy to Cloud Run (one command) and Vertex AI Agent Engine. Versioning, rollback, and monitoring.
Working Examples Built in Class
LLM-as-judge eval suite, Langfuse tracing, token-cost dashboard, prompt-injection and PII guardrail callbacks.
Full multi-agent system with tools, RAG, MCP, evaluation, guardrails, tracing — deployed to Cloud Run.
Teams demo their systems. Peer review and scoring: Best Architecture, Best Evaluation, Most Production-Ready.
Certificate of completion, curated resource guide, community links, self-study Colabs for fine-tuning, and Q&A.
Who Should Attend?
This intensive is designed for technical professionals who want to become Forward Deployed Engineers — building and deploying production-grade AI systems directly with clients. Read what FDE hiring looks like in Malaysia →
Software Engineers & Developers
Engineers building AI-powered applications and integrating LLMs into existing systems.
Data Engineers & Data Scientists
Professionals designing data pipelines, analytics systems, and ML infrastructure.
Technical Leads & Solutions Architects
Leaders responsible for AI engineering strategy, architecture decisions, and team upskilling.
DevOps & Platform Engineers
Teams deploying, monitoring, and scaling AI systems in production environments.
Prerequisites
Experience the Workshop
Join a growing community of Forward Deployed Engineers across Malaysia.
Our People
Learn from Malaysia's top AI engineering and Forward Deployed Engineering practitioners.
Assoc. Prof. Ts. Dr. Yu Yong Poh
Data Science & AI Specialist
Assoc. Prof. Ts. Dr. Yu Yong Poh brings over 15 years of expertise in Data Science and Artificial Intelligence. Formerly the Head of Data Science at a commercial bank, where he spearheaded major enterprise data and AI initiatives, he also delivers end-to-end consultancy and data solutions across diverse sectors, including healthcare, manufacturing, and digital marketing. An experienced corporate trainer, Dr. Yu regularly conducts professional programs in AI, Machine Learning, and Big Data Analytics. He holds an engineering Ph.D. from Universiti Malaya and is an MBOT-registered Professional Technologist.
LinkedIn
Goh Man Fye
Founder, Wistify · AI for Healthcare
Pharmacist-turned-data scientist and founder of Wistify Sdn Bhd (Medcare Pharmacy Management). Holds a Master in Data Science & Analytics. Built production AI for triage, medical scribing and diabetic-retinopathy screening, plus public-health tools My Blue Book and WhereMyMask. National speaker on AI governance and health-data infrastructure.
LinkedIn
Detailed FAQ
Addressing your technical, logistical, and HRDC inquiries.
Course Fee
Transparent pricing for your path to becoming a Forward Deployed Engineer.
Self-Funded (non-HRDC)
Kickstart your Forward Deployed Engineer journey
- 3 full days of intensive training
- Complete course materials & templates
- Certificate of Completion
- 3-month post-training support
- Private community access
HRDC-Claimable
Become a Forward Deployed Engineer with your company's HRDC grant
- 3 full days of intensive training
- Complete course materials & templates
- Certificate of Completion
- 3-month post-training support
- Private community access
Private Corporate Training
In-house for teams of 20 participants and above
- The full 3-day programme, run exclusively for your team
- Examples and exercises tailored to your industry and data
- Dates scheduled around your team, at your office or a venue of your choice
- 100% HRDC claimable under SBL-KHAS — we prepare the paperwork
- Certificate of Completion for every participant
About AITraining2U
AITraining2U was established by professionals to close the divide between academic theory, business and practical industry demands. Our mission is to ensure that AI education translates directly into measurable, real-world results. Since 2025, we have upskilled over 1,800 professionals across Malaysia in AI, Business Transformation, Agentic Automation, and Vibe Coding.
Driven by a core philosophy of "100%-focus on success" our expert faculty delivers highly interactive, hands-on learning experiences focused entirely on implementation. We don't just teach prompt engineering; we teach you how to architect robust, autonomous systems.
Whether through bespoke corporate masterclasses or intensive public bootcamps, we actively partner with enterprise leaders, technical specialists, and government bodies to accelerate their digital transformation journey and build confident, AI-native organizations.