Bespoke Applied Artificial Intelligence and LLM Engineering with Python Training Course
Course Overview
This practical training is tailored for professionals with a data engineering background who wish to develop hands-on expertise in artificial intelligence, Python, and large language models. The curriculum emphasises real-world applications, encompassing model utilisation, prompt engineering, and the creation of AI-driven solutions. Participants will navigate through progressive exercises that transition from foundational concepts to the development of deployable AI workflows.
Training Format
• In-person classroom-based training
• Instructor-led sessions featuring guided practice
• Interactive discussions and real-world case studies
• Daily hands-on exercises
Course Objectives
• Comprehend core AI and machine learning concepts pertinent to contemporary applications
• Enhance Python skills for AI development and data workflows
• Gain an understanding of how large language models function and how to utilise them effectively
• Design and optimise prompts to ensure reliable outputs
• Construct end-to-end AI solutions using APIs and frameworks
• Integrate AI capabilities into data engineering pipelines
This course is available as onsite live training in New Zealand or online live training.
Course Outline
Course Outline Training Proposal
Day 1 - Introduction to AI and Python for Data Workflows
• Overview of the artificial intelligence and machine learning landscape
• The role of AI in modern data engineering
• Python fundamentals refresher for AI applications
• Working with data using pandas and NumPy
• Introduction to APIs and JSON data handling
• Mini exercise loading and transforming datasets
Day 2 - Machine Learning Foundations for Practitioners
• Supervised and unsupervised learning concepts
• Feature engineering and data preparation techniques
• Model training basics using scikit-learn
• Model evaluation and performance metrics
• Introduction to model deployment concepts
• Hands-on building a simple predictive model
Day 3 - Introduction to LLMs and Prompt Engineering
• Understanding large language models and their operation
• Tokenization, context windows, and limitations
• Prompt design principles and techniques
• Zero-shot and few-shot prompting
• Prompt evaluation and iteration strategies
• Hands-on prompt engineering exercises
Day 4 - Building AI Applications with LLMs
• Using LLM APIs in Python
• Structured outputs and function calling concepts
• Building chat-based and task-based applications
• Introduction to retrieval augmented generation
• Connecting LLMs with external data sources
• Mini project building a simple AI assistant
Day 5 - Productionizing AI Solutions
• Designing scalable AI workflows
• Integrating AI into data pipelines
• Monitoring and improving model performance
• Cost optimization and API usage strategies
• Security and responsible AI considerations
• Final project building an end-to-end AI solution
Open Training Courses require 5+ participants.
Bespoke Applied Artificial Intelligence and LLM Engineering with Python Training Course - Booking
Bespoke Applied Artificial Intelligence and LLM Engineering with Python Training Course - Enquiry
Bespoke Applied Artificial Intelligence and LLM Engineering with Python - Consultancy Enquiry
Testimonials (2)
Examples/exercices perfectly adapted to our domain
Luc - CS Group
Course - Scaling Data Analysis with Python and Dask
The trainer was very available to answer all te kind of question I did
Caterina - Stamtech
Course - Developing APIs with Python and FastAPI
Provisional Upcoming Courses (Require 5+ participants)
Related Courses
Advanced LangGraph: Optimization, Debugging, and Monitoring Complex Graphs
35 HoursLangGraph is a framework for building stateful, multi-actor LLM applications as composable graphs with persistent state and control over execution.
This instructor-led, live training (available online or on-site) is designed for advanced-level AI platform engineers, AI-focused DevOps professionals, and ML architects who aim to optimise, debug, monitor, and operate production-grade LangGraph systems.
By the end of this training, participants will be able to:
- Design and optimise complex LangGraph topologies for speed, cost-efficiency, and scalability.
- Engineer reliability through retries, timeouts, idempotency, and checkpoint-based recovery.
- Debug and trace graph executions, inspect state, and systematically reproduce production issues.
- Instrument graphs with logs, metrics, and traces, deploy to production, and monitor SLAs and costs.
Course Format
- Interactive lectures and discussions.
- Extensive exercises and hands-on practice.
- Real-world implementation in a live-lab environment.
Course Customisation Options
- To request a customised training session for this course, please contact us to arrange.
Building Coding Agents with Devstral: From Agent Design to Tooling
14 HoursDevstral is an open-source framework designed for building and running coding agents that can interact with codebases, developer tools, and APIs to enhance engineering productivity.
This instructor-led, live training (online or onsite) is aimed at intermediate to advanced-level ML engineers, developer-tooling teams, and SREs who wish to design, implement, and optimise coding agents using Devstral.
By the end of this training, participants will be able to:
- Set up and configure Devstral for coding agent development.
- Design agentic workflows for codebase exploration and modification.
- Integrate coding agents with developer tools and APIs.
- Implement best practices for secure and efficient agent deployment.
Course Format
- Interactive lectures and discussions.
- Abundant exercises and practice opportunities.
- Hands-on implementation within a live-lab environment.
Course Customisation Options
- To request a customised training session for this course, please contact us to arrange.
Scaling Data Analysis with Python and Dask
14 HoursThis instructor-led, live training in New Zealand (delivered online or on-site) is aimed at data scientists and software engineers who wish to leverage Dask within the Python ecosystem to build, scale, and analyse large datasets.
By the end of this training, participants will be able to:
- Set up the environment to begin building big data processing solutions with Dask and Python.
- Explore the features, libraries, tools, and APIs available in Dask.
- Understand how Dask accelerates parallel computing in Python.
- Learn how to scale the Python ecosystem (NumPy, SciPy, and Pandas) using Dask.
- Optimise the Dask environment to maintain high performance when handling large datasets.
Data Analysis with Python, Pandas and Numpy
14 HoursThis instructor-led, live training in New Zealand (online or on-site) is designed for intermediate-level Python developers and data analysts seeking to enhance their skills in data analysis and manipulation using Pandas and NumPy.
By the end of this training, participants will be able to:
- Set up a development environment including Python, Pandas, and NumPy.
- Create a data analysis application using Pandas and NumPy.
- Perform advanced data wrangling, sorting, and filtering operations.
- Conduct aggregate operations and analyse time series data.
- Visualise data using Matplotlib and other visualisation libraries.
- Debug and optimise their data analysis code.
Open-Source Model Ops: Self-Hosting, Fine-Tuning and Governance with Devstral & Mistral Models
14 HoursDevstral and Mistral models are open-source AI technologies designed for flexible deployment, fine-tuning, and scalable integration.
This instructor-led, live training (online or on-site) is aimed at intermediate–level to advanced–level ML engineers, platform teams, and research engineers who wish to self-host, fine-tune, and govern Mistral and Devstral models in production environments.
By the end of this training, participants will be able to:
- Set up and configure self-hosted environments for Mistral and Devstral models.
- Apply fine-tuning techniques for domain-specific performance.
- Implement versioning, monitoring, and lifecycle governance.
- Ensure security, compliance, and responsible usage of open-source models.
Course Format
- Interactive lecture and discussion.
- Hands-on exercises in self-hosting and fine-tuning.
- Live-lab implementation of governance and monitoring pipelines.
Course Customisation Options
- To request a customised training session for this course, please contact us to arrange.
FARM (FastAPI, React, and MongoDB) Full Stack Development
14 HoursThis instructor-led, live training (available online or on-site) is designed for developers eager to harness the FARM (FastAPI, React, and MongoDB) stack to build dynamic, high-performance, and scalable web applications.
By the conclusion of this training, participants will be able to:
- Establish the essential development environment integrating FastAPI, React, and MongoDB.
- Grasp the core concepts, features, and advantages of the FARM stack.
- Learn how to construct REST APIs using FastAPI.
- Master the art of designing interactive applications with React.
- Develop, test, and deploy both front-end and back-end applications using the FARM stack.
Developing APIs with Python and FastAPI
14 HoursThis instructor-led, live training in New Zealand (online or on-site) is designed for developers who wish to leverage FastAPI with Python to build, test, and deploy RESTful APIs more efficiently and rapidly.
By the end of this training, participants will be able to:
- Set up the necessary development environment to build APIs using Python and FastAPI.
- Create APIs more quickly and easily using the FastAPI library.
- Learn how to define data models and schemas based on Pydantic and OpenAPI.
- Connect APIs to a database using SQLAlchemy.
- Implement security and authentication mechanisms in APIs using FastAPI tools.
- Build container images and deploy web APIs to a cloud server.
Fiji: Image Processing for Biotechnology and Toxicology
14 HoursThis instructor-led, live training in New Zealand (online or onsite) is aimed at beginner-level to intermediate-level researchers and laboratory professionals who wish to process and analyse images related to histological tissues, blood cells, algae, and other biological samples.
By the end of this training, participants will be able to:
- Navigate the Fiji interface and utilise ImageJ's core functions.
- Preprocess and enhance scientific images for better analysis.
- Analyse images quantitatively, including cell counting and area measurement.
- Automate repetitive tasks using macros and plugins.
- Customise workflows for specific image analysis needs in biological research.
LangGraph Applications in Finance
35 HoursLangGraph is a framework for building stateful, multi-actor LLM applications as composable graphs with persistent state and control over execution.
This instructor-led, live training (online or onsite) is aimed at intermediate-level to advanced-level professionals who wish to design, implement, and operate LangGraph-based finance solutions with proper governance, observability, and compliance.
By the end of this training, participants will be able to:
- Design finance-specific LangGraph workflows aligned to regulatory and audit requirements.
- Integrate financial data standards and ontologies into graph state and tooling.
- Implement reliability, safety, and human-in-the-loop controls for critical processes.
- Deploy, monitor, and optimise LangGraph systems for performance, cost, and SLAs.
Format of the Course
- Interactive lecture and discussion.
- Lots of exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customisation Options
- To request a customised training for this course, please contact us to arrange.
LangGraph Foundations: Graph-Based LLM Prompting and Chaining
14 HoursLangGraph is a framework for building graph-structured LLM applications that support planning, branching, tool use, memory, and controllable execution.
This instructor-led, live training (online or onsite) is aimed at beginner-level developers, prompt engineers, and data practitioners who wish to design and build reliable, multi-step LLM workflows using LangGraph.
By the end of this training, participants will be able to:
- Explain core LangGraph concepts (nodes, edges, state) and when to use them.
- Build prompt chains that branch, call tools, and maintain memory.
- Integrate retrieval and external APIs into graph workflows.
- Test, debug, and evaluate LangGraph apps for reliability and safety.
Course Format
- Interactive lecture and facilitated discussion.
- Guided labs and code walkthroughs in a sandbox environment.
- Scenario-based exercises on design, testing, and evaluation.
Course Customisation Options
- To request a customised training for this course, please contact us to arrange.
LangGraph in Healthcare: Workflow Orchestration for Regulated Environments
35 HoursLangGraph enables stateful, multi-actor workflows powered by large language models (LLMs), offering precise control over execution paths and state persistence. In the healthcare sector, these capabilities are vital for ensuring compliance, interoperability, and the development of decision-support systems that align seamlessly with clinical workflows.
This instructor-led, live training (available online or on-site) is designed for intermediate to advanced-level professionals who wish to design, implement, and manage LangGraph-based healthcare solutions while navigating regulatory, ethical, and operational challenges.
By the end of this training, participants will be able to:
- Design healthcare-specific LangGraph workflows with compliance and auditability as core considerations.
- Integrate LangGraph applications with medical ontologies and standards such as FHIR, SNOMED CT, and ICD.
- Apply best practices for reliability, traceability, and explainability within sensitive healthcare environments.
- Deploy, monitor, and validate LangGraph applications in real-world healthcare production settings.
Course Format
- Interactive lectures and group discussions.
- Hands-on exercises featuring real-world case studies.
- Practical implementation in a live-lab environment.
Course Customisation Options
- To request a customised version of this training, please contact us to arrange a tailored session.
LangGraph for Legal Applications
35 HoursLangGraph is a framework for building stateful, multi-actor LLM applications as composable graphs with persistent state and precise control over execution.
This instructor-led, live training (online or onsite) is aimed at intermediate-level to advanced-level professionals who wish to design, implement, and operate LangGraph-based legal solutions with the necessary compliance, traceability, and governance controls.
By the end of this training, participants will be able to:
- Design legal-specific LangGraph workflows that preserve auditability and compliance.
- Integrate legal ontologies and document standards into graph state and processing.
- Implement guardrails, human-in-the-loop approvals, and traceable decision paths.
- Deploy, monitor, and maintain LangGraph services in production with observability and cost controls.
Format of the Course
- Interactive lecture and discussion.
- Plenty of exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customisation Options
- To request a customised training for this course, please contact us to arrange.
Building Dynamic Workflows with LangGraph and LLM Agents
14 HoursLangGraph is a framework for composing graph-structured LLM workflows that support branching, tool use, memory, and controllable execution.
This instructor-led, live training (online or on-site) is aimed at intermediate-level engineers and product teams who wish to combine LangGraph's graph logic with LLM agent loops to build dynamic, context-aware applications such as customer support agents, decision trees, and information retrieval systems.
By the end of this training, participants will be able to:
- Design graph-based workflows that coordinate LLM agents, tools, and memory.
- Implement conditional routing, retries, and fallbacks for robust execution.
- Integrate retrieval, APIs, and structured outputs into agent loops.
- Evaluate, monitor, and harden agent behaviour for reliability and safety.
Format of the Course
- Interactive lecture and facilitated discussion.
- Guided labs and code walkthroughs in a sandbox environment.
- Scenario-based design exercises and peer reviews.
Course Customisation Options
- To request customised training for this course, please contact us to arrange.
LangGraph for Marketing Automation
14 HoursLangGraph is a graph-based orchestration framework that enables conditional, multi-step LLM and tool workflows, ideal for automating and personalising content pipelines.
This instructor-led, live training (online or on-site) is aimed at intermediate-level marketers, content strategists, and automation developers who wish to implement dynamic, branching email campaigns and content generation pipelines using LangGraph.
By the end of this training, participants will be able to:
- Design graph-structured content and email workflows with conditional logic.
- Integrate LLMs, APIs, and data sources for automated personalisation.
- Manage state, memory, and context across multi-step campaigns.
- Evaluate, monitor, and optimise workflow performance and delivery outcomes.
Format of the Course
- Interactive lectures and group discussions.
- Hands-on labs implementing email workflows and content pipelines.
- Scenario-based exercises on personalisation, segmentation, and branching logic.
Course Customisation Options
- To request a customised training for this course, please contact us to arrange.
Accelerating Python Pandas Workflows with Modin
14 HoursThis instructor-led, live training in New Zealand (available online or on-site) is tailored for data scientists and developers who wish to utilise Modin to build and implement parallel computations with Pandas, enabling faster data analysis.
By the end of this training, participants will be able to:
- Set up the necessary environment to begin developing scalable Pandas workflows with Modin.
- Understand the features, architecture, and advantages of Modin.
- Identify the key differences between Modin, Dask, and Ray.
- Execute Pandas operations more efficiently using Modin.
- Implement the full Pandas API and its associated functions.
