AI Forward Deployed Engineer with Work Experience

Dr. Aki Wijesundara

PhD in ML | Google AI Accelerator Alum

Manu Jayawardana

Exited AI Founder | Founder, TAI Labs

This course is popular

7 people enrolled last week.

Take a client problem from discovery to a deployed AI solution in 6 weeks.

FDE roles hire people who can ship for a client, not just pass a quiz. Companies like OpenAI, Anthropic and Palantir put Forward Deployed Engineers in front of customers to turn messy business problems into working AI. That takes scoping, building, testing and handing over, under real constraints.

You learn it by doing it. Four weeks of live teaching, then a two-week simulated client engagement where we play your stakeholders, send a change request and review your handover.

What you'll build:

  • A scoped AI app from a real client request

  • RAG over business data with citations and access boundaries

  • An agent that updates a sandbox ticketing system after human approval

  • Evals, a deployment and a client acceptance report

We're an official Anthropic training partner. TAI courses are taught by practitioners who ship AI systems for clients every week. Students come from Google, Meta, OpenAI, McKinsey and BCG.

You leave with a deployed portfolio project and the client experience to talk about in an FDE interview.

What you’ll learn

Scope, build, evaluate and hand over an AI solution for a client: LLM APIs, RAG, agents, MCP, memory and evals, across 6 weeks.

  • Map a business workflow and decide where code, AI or human judgment belongs

  • Define requirements, success criteria and the right level of autonomy before you build

  • Build a basic agent loop with tool calling, structured outputs and stop conditions

  • Build ingestion and retrieval with keyword, vector and hybrid search, plus reranking

  • Generate grounded answers with citations and flag when the evidence is insufficient

  • Preserve access boundaries and test retrieval quality before a client sees it

  • Use LangGraph for state, routing and execution, and connect tools through APIs and MCP

  • Add human approval, scoped credentials, audit logs, retries and execution limits

  • Choose between session state, persistent memory, reusable skills and subagents

  • Capture traces, group failures and turn client success criteria into eval cases

  • Combine deterministic checks, human review and calibrated LLM judges

  • Measure quality, cost per task and latency, and test for prompt injection and leaks

  • Deploy from a starter template with secrets management, monitoring and rollback

  • Gate changes on agreed evals so regressions never reach the client

  • Present results, limitations and operating instructions to stakeholders

  • Scope an ambiguous brief, agree acceptance criteria and build a working pilot

  • Handle a client change request mid-sprint, then test, deploy and document

  • Submit a solution brief, repo, eval report, 5-minute demo and handover guide

Learn directly from Aki & Manu

Dr. Aki Wijesundara

Dr. Aki Wijesundara

AI Founder | Educator | Google AI Accelerator Alum

Google
Meta
Amazon Web Services
OpenAI
NVIDIA
Manu Jayawardana

Manu Jayawardana

AI Advisor | Founder, TAI Labs

Previous Students from
OpenAI
Boston Consulting Group (BCG)
NVIDIA
Google
McKinsey & Company
See all products from TAI Labs

Who this course is for

  • The engineer moving into FDE. Software, data or ML. You want client-facing AI delivery experience, not another tutorial.

  • The consultant or solutions engineer. You already work with clients. Now you need to scope, build and ship the AI yourself.

  • The career mover. Targeting FDE or AI engineering roles. You need a deployed client project to point to in interviews.

Prerequisites

  • Some code, or willingness to pick it up

    You do not need to be a strong coder. We build with coding agents, so you skill up as you build. Comfort with basic logic helps.

  • A coding agent to build with

    We use Claude Code and Cursor. They let you write and understand real code fast. Setup is covered in pre-course.

  • Time for a two-week client sprint

    Weeks 5 and 6 are a simulated client engagement. Plan for focused build time to scope, ship and hand over your project.

What's included

Live sessions

Learn directly from Dr. Aki Wijesundara & Manu Jayawardana in a real-time, interactive format.

Live build sessions

Four 2-hour live sessions on Mondays, one per teaching week, where you build with Aki and Manu. Every session ends with something working and pushed to your repo.

A 2-week FDE Industry Project Sprint

Two weeks of simulated client work. You get a realistic brief, sample business data and sandbox systems. We act as your client stakeholders, answer questions and send a change request.

A deployed portfolio project

Deliver an AI Support Operations Assistant: retrieval, a sandbox integration, approval before external actions, evals and a deployment. The project you talk through in an FDE interview.

Mentor feedback and assessment

Your submission is assessed on scoping, implementation, evaluation, deployment and client communication, with written feedback you can act on.

Weekly office hours

Six optional 45-minute office hours on Tuesdays for code review, debugging help and feedback on your project.

Lifetime access

Revisit every lesson, recording, notebook and code repository whenever you need. Your access does not expire.

Every repo and template, yours forever

Keep the starter templates, agent code, eval harness and handover templates. Reuse them on your own clients and products.

Community of peers

Join a cohort of engineers and consultants targeting the same roles. Stay accountable, swap solutions and review each other's work.

Certificate of completion

Earn a certificate to share with employers and add to LinkedIn. The real proof is the deployed client project you leave with.

Maven Guarantee

Your purchase is backed by the Maven Guarantee.

Course syllabus

25 lessons • 6 projects

Week 1

Nov 26—Nov 29

    Week 1 materials: AI foundations and client discovery

    5 items

Week 2

Nov 30—Dec 6

    Week 2 materials: RAG and business data

    5 items

Testimonials

  • The AI training approach is outstanding. Our team learned to build practical AI solutions that we could implement immediately in our educational platform. The hands-on methodology made complex AI concepts accessible to our entire development team.
    Testimonial author image

    Kavi T.

    CEO of Tilli Kids / Stanford PhD
  • Not only are the instructors experts in their field, they're incredibly skilled at breaking down complicated AI concepts so students can grasp them quickly. Anyone interested in building foundational AI knowledge should take this training - it's worth the investment.
    Testimonial author image

    Dr. Elizabeth Creighton

    Founder & Principal at Brazen
  • The instructors help break down AI model development and clearly have plenty of experience to help others learn about complex concepts like infrastructure setup. The practical approach to NLP and LLM applications was exactly what our team needed.
    Testimonial author image

    Alissa Valentine

    NLP & LLM Real World Data Scientist
  • I sent my team through this training for upskilling, and the results have been remarkable. Within weeks, they became much more efficient at building automations and deploying AI agents at work. This program bridges the gap between theory and practice and it’s had a real impact on our productivity.
    Testimonial author image

    Aamir Faaiz

    CEO of Bayseian

AI Evals under 3 minutes

AI Evals

Who You'll Be Learning From

Learn from Aki & Manu. Previous students are from top companies like Google, Meta & OpenAI.

Tools that you will learn

Hear It From Our Students

Learning AI Made Simple | Student Feedback on Our AI Engineering Bootcamp | TAI

Student Feedback on Our Bootcamp

Irena Palamani Xhurxhi Ph.D. AI/ML , Walmart

Our community of learners

A single snapshot of learners across our AI courses and programs.

Frequently asked questions

Maven for Teams

Reimbursement

Get your company to pay

Everything L&D needs: email template, receipts, and certificate of completion.

Get reimbursed

Team discount

Learn with your teammates

Save 20%+ when 2 or more teammates enroll in the same cohort.

Save 20%+ with a team

Private cohort

Run a cohort for your org

A dedicated cohort with a custom schedule and curriculum, tailored to your team.

Book a private cohort

$399

USD

7 days left to enroll

Nov 26—Jan 10
Enroll