AI bootcamp 2
This advanced AI Bootcamp teaches you to design, debug, and optimize full-stack AI systems that adapt over time. You will master byte-level models, advanced decoding, and RAG architectures that integrate text, images, tables, and structured data. You will learn multi-vector indexing, late interaction, and reinforcement learning techniques like DPO, PPO, and verifier-guided feedback. Through 50+ hands-on labs using Hugging Face, DSPy, LangChain, and OpenPipe, you will graduate able to architect, deploy, and evolve enterprise-grade AI pipelines with precision and scalability.
- 5.0 / 5 (1 rating)
- Published
- Updated
Dr. Dipen
I am an AI/ML researcher with 150+ citations and 16 published research papers. I have three tier-1 publications, including Internet of Things (Elsevier), Biomedical Signal Processing and Control (Elsevier), and IEEE Access. In my research journey, I have collaborated with NASA Glenn Research Center, Cleveland Clinic, and the U.S. Department of Energy for various research projects. I am also an official reviewer and have reviewed over 100 research papers for Elsevier, IEEE Transactions, ICRA, MDPI, and other top journals and conferences. I hold a PhD from Cleveland State University with a focus on large language models (LLMs) in cybersecurity, and I also earned a master’s degree in informatics from Northeastern University.
zaoyang
Owner of \newline and previously co-creator of Farmville (200M users, $3B revenue) and Kaspa ($3B market cap). Self-taught in gaming, crypto, deep learning, now generative AI. Newline is used by 250,000+ professionals from Salesforce, Adobe, Disney, Amazon, and more. Newline has built editorial tools using LLMs, article generation using reinforcement learning and LLMs, instructor outreach tools. Newline is currently building generative AI products that will be announced soon.
01Remote
You can take the course from anywhere in the world, as long as you have a computer and an internet connection.
02Self-Paced
Learn at your own pace, whenever it's convenient for you. With no rigid schedule to worry about, you can take the course on your own terms.
03Community
Join a vibrant community of other students who are also learning with AI bootcamp 2. Ask questions, get feedback and collaborate with others to take your skills to the next level.
04Structured
Learn in a cohesive fashion that's easy to follow. With a clear progression from basic principles to advanced techniques, you'll grow stronger and more skilled with each module.
AI engineering in the enterprise
Master byte-level language models and advanced decoding strategies like top-k, nucleus, and speculative decoding
Design and optimize advanced Retrieval-Augmented Generation (RAG) pipelines that integrate text, images, tables, and structured data
Implement multi-vector indexing, late interaction methods, and metadata-aware query routing
Fine-tune retrievers and rerankers using contrastive loss, triplet loss, and hard-negative mining
Simulate and enhance reasoning in non-CoT models using feedback loops and model control patterns
Develop tool-using agents with multi-hop planning, disambiguation flows, and function-calling capabilities
Build feedback-driven evaluation pipelines using persona-based synthetic queries, regex/schema validators, and topic clustering
Learn and apply reinforcement learning techniques including DPO, PPO, GPRO, RLVR, and verifier-guided optimization
Integrate open-source frameworks like Hugging Face, DSPy, LangChain, OpenPipe, and Braintrust into production-grade systems
Deploy enterprise-ready AI systems with robust evaluation, monitoring, and continuous improvement loops
Architect modular, future-proof AI pipelines that can evolve with new models, tools, and retrieval methods
In this bootcamp, we go beyond prompt engineering to give you the skills to design, build, and optimize advanced AI systems that can adapt and improve over time. You will learn to think like a systems engineer, mastering the underlying mechanics of modern models and the techniques that make them perform in real-world, high-stakes environments.
Over several intensive weeks, we combine:
Deep technical instruction with hands-on coding projects to bridge the gap between theory and deployment. You’ll work directly with production-grade frameworks, simulate complex reasoning behaviors, and build AI pipelines that integrate multiple data types and modalities. Every concept is reinforced through practical exercises, live feedback, and real-world project reviews, ensuring that by the end, you can not only understand advanced AI architectures but also architect, deploy, and refine them for evolving enterprise needs. This program includes in-depth instruction, dedicated mentorship, and exclusive access to tools, templates, and a collaborative community to support your continued growth.
Your expert guides through this bootcamp are:
Dr. Dipen Bhuva: Dr. Dipen is an AI/ML researcher with 150+ citations and 16 published research papers. He has 3 tier-1 publications, including Internet of Things (Elsevier), Biomedical Signal Processing and Control (Elsevier), and IEEE Access. In his research journey, he has collaborated with NASA-Glenn Centre, Cleveland Clinic, and the US department of energy for his research papers. He was an official reviewer and has reviewed 100+ research papers from Elsevier, IEEE Transactions, ICRA, MDPI, and other top journals and conferences. He has a PhD from Cleveland State University with a focus on LLMs in cybersecurity. He also has a master's in informatics at Northeastern University.
Zao Yang: Zao is the owner of Newline, a platform used by 150k professionals from companies like Salesforce, Adobe, Disney, and Amazon. Zao has a rich history in the tech industry, co-creating Farmville (200 million users, $3B revenue) and Kaspa ($3B market cap). Self-taught in deep learning, generative AI, and machine learning, Zao is passionate about empowering others to develop practical AI applications. His extensive knowledge of both the technical and business sides of AI projects will be invaluable as you work on your own.
With Dipen and Zao's guidance, you’ll gain practical insights into building and deploying advanced AI models, preparing you for the most challenging and rewarding roles in the AI field.
AI engineering in the enterprise
Ability to architect and deploy advanced AI systems for enterprise and consulting, worth $100k in annual value ($1M over 10 years)
Skills in advanced RAG, RLHF, and RL-based fine-tuning that are rare and in high demand at top AI companies
Capability to build multimodal, feedback-driven AI pipelines that outperform vanilla retrieval and generation systems
Technical mastery to lead or consult on AI platform engineering, unlocking six-figure consulting opportunities
Portfolio of 50+ hands-on labs and multiple enterprise-grade AI projects to showcase to employers or clients
Direct code reviews, debugging help, and system design feedback from expert instructors
Future-proof understanding of AI system architecture, enabling you to adapt to new models and frameworks as they emerge
A competitive advantage in the AI job market, with potential to increase earnings by $50k+ annually
Our students work at
Bootcamp Syllabus and Content
Byte-Level Models & Sampling Decoders
3 Units
- 01Tokenization deep dive - Byte-level language modeling vs traditional tokenization
- Learn how byte-level models process raw UTF-8 bytes directly, with a vocabulary size of 256
- Understand how this approach removes the need for subword tokenizers like BPE or SentencePiece
- Compare byte-level models to tokenized models with larger vocabularies (e.g., 30k–50k tokens)
- Analyze the trade-offs between the two approaches in terms of simplicity
- Evaluate how each approach handles multilingual text
- Assess the impact on model size
- Examine differences in performance
- 02State-of-the-art decoders
-
Explore decoding strategies that influence LLM output diversity and fluency
-
Top-k sampling
- Learn how Top-k sampling truncates the output distribution to the k most likely tokens (e.g., k=16)
- Understand how Top-k sampling balances creativity and control, and why it’s especially effective with small vocab sizes like byte-level models
-
Nucleus (Top-p) sampling
- Learn how Nucleus (Top-p) sampling dynamically includes tokens up to a cumulative probability p (e.g., p=0.9)
- Understand how Top-p sampling produces more adaptive and coherent completions than Top-k, especially in unpredictable generation tasks
-
Beam search
- Learn how Beam search keeps multiple candidate completions in parallel and scores them to select the most likely overall path
- Understand why Beam search is useful for deterministic outputs (e.g., code, structured data) and why it can lead to repetitive or bland completions in open-ended generation
-
Speculative decoding (OpenAI-style)
- Learn how Speculative decoding speeds up inference by letting a small model propose multiple token candidates in parallel, which a larger model verifies
- Understand how speculative decoding works internally and why it is gaining popularity in production systems like Groq and OpenAI APIs
-
- 03Mini-lab - Compare decoding methods on a complex prompt
- Run the same input prompt using Top-k, Top-p, and Beam search decoding
- Measure differences in diversity, accuracy, repetition, and latency across the methods
- Discuss which strategy works best for each context and explain why
Markov Chains & Reinforcement Learning Foundations
4 Units
- 01Markov Decision Processes (MDP) as LLM analogies
- Learn how token generation in LLMs can be framed as a Markov process
- Understand the key components of an MDP
- Understand how these map conceptually to autoregressive decoding
- 02Monte Carlo vs Temporal Difference (TD) learning
- Explore the Monte Carlo and TD methods of learning from sequences
- 03Q-learning & Policy Gradients (conceptual overview)
- Learn the concept of Q-learning as a method to estimate how good an action (token) is in a specific context (prompt state)
- Learn the concept of Policy gradients as a method to directly optimize the probability distribution over actions to maximize long-term reward
- Understand how Q-learning and Policy gradients form the basis of RLHF, DPO, and advanced training techniques for aligning LLM behavior
- 04RL in decoding, CoT prompting, and feedback loops
-
Understand how RL ideas are used without training by introducing dynamic feedback in inference
- Apply reward scoring or confidence thresholds to adjust CoT (Chain-of-Thought) reasoning steps
- Use external tools (e.g., validators or search APIs) as part of a feedback loop that rewards correct or complete answers
- Understand how RL concepts power speculative decoding verification, scratchpad agents, and dynamic rerouting during generation
-
Advanced Retrieval Methods
9 Units
- 01Cartridge-based retrieval (self-study distillation)
- Learn how to modularize retrieval into topic- or task-specific “cartridges.”
- Understand that cartridges are pre-distilled context sets for self-querying agents
- Study how this approach is inspired by OpenAI’s retrieval plugin and LangChain’s retriever routers
- See how cartridges improve retrieval precision by narrowing memory to high-relevance windows
- 02Late interaction methods (ColQwen-Omni, audio+image chunks)
- Study late interaction architectures (like ColQwen-Omni) that separate dense retrieval from deep semantic fusion
- Explore how these models support chunking and retrieval over image, audio, and video-text combinations using attention-based fusion at scoring time
- 03Multi-vector DB vs standard DB
- Understand how multi-vector databases (e.g., ColBERT, Turbopuffer) store multiple vectors per document to support fine-grained relevance
- Contrast this with standard single-vector-per-doc retrieval (e.g., FAISS), and learn when multi-vector setups are worth the extra complexity
- 04Query routing logic and memory-index hybrids
-
Implement index routing systems where queries are conditionally routed:
- short factual query → lexical index
- long reasoning query → dense retriever
- visual question → image embedding index
-
Learn how to fuse local memory with global vector stores for agentic long-term retrieval
-
- 05Contrastive loss vs triplet loss
- Compare the two core objectives used for fine-tuning retrievers
- Understand how each behaves in hard-negative-rich domains like code or finance
- 06Tri-encoder vs cross-encoder performance trade-offs
- Explore the architectural trade-offs between Bi/tri-encoders vs cross-encoders
- Learn when to use hybrid systems (e.g., bi-encoder retrieval + cross-encoder reranking)
- 07Triplet-loss fundamentals and semi-hard negative mining
- Dive into triplet formation strategies
- Focusing on how to find semi-hard negatives (similar but incorrect results that challenge the model)
- 08Cohere Rerank API & SBERT fine-tuning ([sbert.net], Hugging Face)
- Learn to use off-the-shelf rerankers like Cohere’s API or fine-tune SBERT models to optimize document ranking post-retrieval
- 09Hard-negative mining strategies
- Implement pipelines that automatically surface confusing negatives
Subscribe for a Free Lesson
By subscribing to the newline newsletter, you will also receive weekly, hands-on tutorials and updates on upcoming courses in your inbox.
Meet the Bootcamp Instructor
Purchase the bootcamp today
One-Time Purchase
AI bootcamp 2
- Discord Community Access
- Full Transcripts
- Project Completion Guarantee
- Lifetime Access
Frequently Asked Questions
How is this different from other AI bootcamps?
Most AI bootcamps focus on either beginner programming with AI APIs or narrow workflows like basic RAG or fine-tuning. Bootcamp 2 is designed for engineers who want to master advanced AI systems engineering — including byte-level modeling, multi-vector and multimodal RAG, reinforcement learning (DPO, PPO, RLVR), verifier-guided pipelines, and tool-using agents. It combines deep technical theory with 50+ hands-on labs to build production-ready systems. To my knowledge, few programs cover advanced RAG and RLHF together at this depth, especially with a focus on evaluation, feedback loops, and enterprise deployment.
What should I look for in this AI Bootcamp?
Bootcamp 2 is a project-focused program where you learn by building advanced AI pipelines from scratch. It’s built for people who want to go beyond prompt engineering and API wrappers, and gain mastery in byte-level models, reasoning simulation, advanced retrieval architectures, and RL-based fine-tuning. You’ll work on multimodal RAG, feedback-driven rerankers, and RLHF-ready agents — with direct guidance from expert instructors who have shipped large-scale AI products.
Who is this Artificial Intelligence Bootcamp ideal for?
This bootcamp is ideal for engineers, data scientists, and technical founders who want to build enterprise-ready AI systems. Whether you’re implementing advanced RAG for private, on-premise data, fine-tuning models with smaller datasets, or applying RLHF techniques to AI agents, this program equips you with the skills and frameworks needed to operate at a senior level.
Are there any required skills or Python programming experience needed before enrolling?
You must have basic Python programming and debugging skills. This is not a beginner’s AI course — it assumes you can follow code, run experiments, and troubleshoot errors. Prior completion of Bootcamp 1 or equivalent experience is recommended.
What is the course structure?
Weekly commitment is approximately 3 hours for lectures and office hours, plus 2–4 hours of hands-on coding. The program runs for multiple weeks, with 50+ labs and mini-projects, culminating in enterprise-ready systems you can deploy. All sessions are recorded, and live schedules are designed to accommodate different time zones.
Do I need any pre-requisite?
You need to be comfortable programming in Python and committed to completing advanced coding projects. We assume you have completed Bootcamp 1 or have equivalent knowledge of LLM fundamentals.
Anything I need to prepare?
It’s best to come with a project idea — for example, a multimodal RAG system for your company data or an RLHF-tuned assistant for a niche use case. The curriculum is flexible enough to adapt your learning to your goals.
Why should I take the Artificial Intelligence Bootcamp from newline?
Bootcamp 2 is uniquely focused on advanced RAG, reinforcement learning, and RLHF. You’ll learn to design and debug full-stack AI systems with evaluation and feedback loops, not just call APIs. You also get mentorship from practitioners who have shipped large-scale AI systems and can help you adapt the techniques to your own projects.
To what extent will the program delve into generative AI concepts and applications?
This bootcamp goes far beyond generative AI basics. You’ll explore advanced model architectures, reasoning control, retrieval fusion across modalities, RL-based adaptation, and multi-hop agent planning. Everything is taught through runnable code that you can adapt to real-world applications.
What are the career outcomes after completing the AI Bootcamp with newline?
Graduates are equipped for roles such as senior AI engineer, AI systems architect, enterprise AI consultant, and startup founder in the AI space. You will have the skills to build, deploy, and optimize advanced AI systems for enterprise-grade use cases.
Are there any hands-on projects incorporated into the AI Bootcamp curriculum?
Yes. You will complete over 50 labs and multiple large-scale projects, including a full multimodal RAG pipeline, feedback-driven reranker tuning, and RLHF-ready agent deployment. Every project is designed to be directly applicable to real-world scenarios.
Do you have a guarantee?
Yes. If you commit to the work, we guarantee you will complete a project that meets your goals. We will align on project scope, budget, and time commitment upfront, and provide ongoing guidance to ensure you can ship a functional, well-evaluated system.
What is the target audience?
There are three core groups: engineers applying advanced RAG and RL fine-tuning for private data; builders creating vertical foundational models on smaller datasets; and technical professionals leveraging these skills for consulting or AI startup ventures.
Will you be covering multi-modal applications?
Yes. You will build retrieval systems and agents that handle text, images, tables, audio, and structured data — integrating them into unified, query-routed pipelines.
