Are you ready to meet the demands of tomorrow? Evaluate your approach to skilling.

Transform Unstructured Text Into Instant, Accurate Answers

12 Weeks. Live Online Classes. Instructor-led.

Our Partners

Ship multilingual NLP systems with monitoring, guard-rails, and governance baked in

Craft vector & hybrid search pipelines using pgvector, Pinecone, and Elasticsearch

Engineer Retrieval-Augmented Generation (RAG) services that ground LLMs in trusted data

What you will learn?

    • Generate sentence-level embeddings with OpenAI, Cohere & HF models

    • Design efficient HNSW/IVF indexes in pgvector, Pinecone, or Milvus

    • Tune distance metrics, index parameters, and recall/latency trade-offs

    • Combine dense (vector) and sparse (BM25) scores in Elasticsearch hybrid search

    • Train lightGBM / XGBoost learning-to-rank models on click-through logs

    • Evaluate NDCG, MRR, and success@k; instrument A/B experiments

    • Chain retriever → re-ranker → LLM answerer with LangChain or LlamaIndex

    • Apply chunking, metadata filters, and Max Marginal Relevance (MMR) to boost relevancy

    • Expose gRPC/REST API; benchmark answers for factual grounding & latency

    • Fine-tune models (e.g., MiniLM, Mistral-7B) on domain-specific corpora

    • Integrate language detection and neural MT for cross-lingual retrieval

    • Implement transfer-learning tricks to keep GPU bills low

    • Build automatic hallucination & toxicity tests with Promptfoo / Rebuff

    • Stream metrics to Prometheus; create Grafana dashboards for drift & latency

    • Produce governance docs for GDPR, privacy, and data provenance

    • Team POC: policy-search, knowledge-base Q&A, or legal-doc RAG system

    • Deliver architecture diagrams, cost model, and live demo to hiring-manager panel

Turn terabytes of documents into instant, trustworthy answers. You’ll master embeddings, hybrid BM25 + vector ranking, and build multilingual RAG pipelines with pgvector, Pinecone, LangChain and OpenAI. Automated hallucination tests, governance dashboards, and Prometheus monitoring ensure your search or Q&A service stays accurate, compliant, and fast. Ideal for engineers modernising legacy Lucene stacks or delivering AI-powered knowledge bases in finance, legal, or energy sectors.

Who Should Enrol?

  • Upgrade from TF-IDF and keyword scoring to dense-vector retrieval, hybrid rankers and RAG pipelines that beat commercial SaaS search.

  • Add text‐heavy use-cases (chatbots, doc-QA, semantic search) to your model portfolio and learn to serve them with latency and cost SLAs.

  • Move beyond analytics to production-grade NLP: embeddings, transformers, evaluation suites and online A/B relevance tests.

  • Embed vector databases, similarity APIs and streaming ingestion into existing micro-service architectures—without breaking auth or billing.

  • Understand how modern retrieval works so you can scope, prioritise and govern enterprise search projects with vendors or in-house teams.

Professionals who must turn mountains of text into search and Q&A experiences users trust.

Prerequisites
Solid Python & Git, basic ML knowledge. Free Deep Learning Core and Docker-K8s Mini-Camp bridge badges are included for all Intermediate-track graduates.

Career Pathways

  • Build and optimise dense-vector, hybrid and RAG search stacks that power chat, FAQ and knowledge-base experiences.

  • Design offline metrics and online A/B tests, fine-tune LLM rankers and iterate on relevance signals at scale.

  • Integrate embedding services, vector DBs, orchestration frameworks and observability into cloud-native platforms.

  • Scope end-to-end IR solutions for large document corpora, balancing latency, accuracy and cost.

  • Translate business questions into scalable NLP/search architectures and roadmaps that engineering teams can execute.

Graduates leave with a live enterprise search stack (vector DB + RAG API), a publish-ready design doc, and recruiter-ready stories that map to the majority of “Search/NLP Engineer” roles on today’s job boards.

Amir Charkhi
Technology leader | Adjunct Professor | Founder

With 20 + years across energy, mining, finance, and government, Amir turns real-world data problems into production AI. He specialises in MLOps, cloud data engineering, and Python, and now shares that know-how as founder of AI Tech Institute and adjunct professor at UWA, where he designs hands-on courses in machine learning and LLMs.

Advanced: Enterprise NLP & Search

12 Weeks. Live Online Classes. Next Cohort 2nd September

Advanced: Enterprise NLP & Search Advanced: Enterprise NLP & Search
Quick View
Advanced: Enterprise NLP & Search
$4,250.00

  • “In just six weeks I went from zero Python to building a churn-prediction model I could demo at work. I finally feel job-ready.” — Maddie, Data Analyst

  • “The pace was perfect—hands-on from day one and always tied back to real business value. Best learning experience I’ve had online.” — Demian, Mining Engineer

  • “Being a new mum, flexible recordings were a lifesaver. I could pause, practice, and still keep up with the cohort.” — Molly, Graduate Analyst

  • “Clear path: beginner foundations, then straight into their Intermediate Data Science track. No other provider lays out the journey so cleanly.” — Bec, Business Analyst

  • “Projects mirrored the stack we use at work—no toy examples. I deployed my capstone on AWS the same night.” — Amy, Cloud Architect

  • “From pandas to production MLOps in 24 weeks—and I never felt lost. The Slack support channel replies within minutes.” — Arjun, Energy Sector Intern

Frequently Asked Questions

  • Beginner courses: none— we start with Python basics.
    Intermediate & Advanced: ability to write simple Python scripts and use Git is expected.

  • Plan on 8–10 hours: 2× 3-hour live sessions and 2–4 hours of project work. Advanced tracks may require up to 10 hours for capstone milestones.

  • All sessions are recorded and posted within 12 hours. You’ll still have access to Slack/Discord to ask instructors questions.

  • New intakes launch roughly every 8 weeks. Each course page shows the exact start date and the “Apply-by” deadline.

  • Just a laptop with Chrome/Firefox and a stable internet connection. All coding happens in cloud JupyterLab or VS Code Dev Containers—no local installs.

  • Yes. 100 % refund until the end of Week 2—no questions asked. After that, pro-rata refunds apply if you need to withdraw for documented reasons.

  • Absolutely. We issue invoices to companies and offer interest-free 3- or 6-month payment plans.

  • Live Q&A in every session, 24-hour Slack response time from instructors, weekly office-hours, and code reviews on your GitHub pull requests.