AI & Data
Generative AI & LLMs Challenges
Generative AI & LLMs challenges put you inside the work of building with large language models. You'll develop skills in prompt patterns, few-shot prompting, chain-of-thought, and LLM API integration, learning how these models behave before you scale them.
From there you'll handle the harder edges — RAG architectures, vector database basics, fine-tuning, and prompt versioning — putting LLM guardrails and LLM evaluation around every deployment the way AI teams actually do. Each challenge you solve earns a verified credential you can share with recruiters.
- CodeIntermediateNew
Train a Domain-Specific Reranker for a Legal-Tech Search Box
You receive 20,000 (query, document, relevance-label) triples from the firm's contract corpus. Fine-tune a small cross-encoder (e.g., ms-marco-MiniLM-L-6-v2 or BAAI/bge-reranker…
- Cross Encoder Reranker
- Fine Tuning
- Ir Evaluation
Open coursework - CodeIntermediateNew
Fine-Tune ASR for a Healthcare Voice-Note Startup
You receive about 40 hours of de-identified clinician voice notes paired with corrected transcripts plus a medical-terminology lexicon (about 8,000 drug + procedure terms). Fine…
- Asr
- Speech Recognition
- Domain Adaptation
Speech Recognition and Spoken Language Processing - CodeIntermediateNew
LoRA Fine-Tune a 7B LLM for Legal-Clause Extraction
You receive a curated extraction dataset (2,000 train, 500 val, 500 test contracts with span-level labels across 12 clause types) and a fine-tunable 7B base model (e.g., Llama-3…
- Lora
- Fine Tuning
- Parameter Efficient Tuning
Open coursework - CodeIntermediateNew
Build a Vision-Language Search for an E-commerce Catalog
Pick a vision-language encoder (OpenCLIP, SigLIP, or BLIP-2 image-text variant). Index all 600k product images into a vector database (Qdrant/FAISS). Build a query-time pipeline…
- Vision Language Models
- Clip
- Vector Search
Open coursework Practice your coursework on real scenarios.
Every challenge is shaped from real-world context — not generic exercises. The work mirrors what your degree prepares you for.
Why Ewance
- AnalysisBeginnerNew
AI-Powered Customer Sentiment Analysis for a Fintech App
You will receive a dataset of 500+ anonymized app reviews and tweets. Using AI tools like ChatGPT or Claude, you must craft prompts to classify sentiment (positive, negative, ne…
- Prompt Engineering
- Sentiment Analysis
- Data Visualization
Open coursework - AnalysisIntermediateNew
Transfer-Learning Backbone Bake-Off for Retail Product Tagging
You receive 80,000 retail product images tagged with multiple labels from a 250-tag taxonomy. Use each of the three pretrained backbones via two transfer strategies: (1) linear …
- Transfer Learning
- Fine Tuning
- Self Supervised Learning
Open coursework - CodeIntermediateNew
Natural Language Inference for an HR-AI Compliance Tool
Use SNLI/MNLI/ANLI as starting data and curate 200 domain-specific HR examples (synthetic or anonymized) for fine-tuning. Fine-tune a small encoder (DeBERTa-v3-base or similar),…
- Natural Language Inference
- Transformer Models
- Fine Tuning
Open coursework - CodeBeginnerNew
Build Semantic Search for an Internal Engineering Wiki
You receive a Confluence XML export (~12k pages, ~80 MB of text) and a hand-labeled benchmark of 50 internal queries with ground-truth doc IDs. Chunk and embed the corpus with a…
- Embedding Models
- Vector Search
- Pgvector
Vector Databases and Embeddings - Browse challenges
Explore role
Marketing Analyst
Plan and measure campaigns that grow the business. Funnel analytics, attribution, segmentation, and the rigorous measurement that lets marketing defend its budget at the leadership table.
- CodeIntermediateNew
Fine-Tune a Sequence-to-Sequence Model for Code-Doc Generation
Take a small base model (CodeT5+ or a distilled CodeLlama-Instruct). Build the dataset by mining around 8,000 high-quality function-docstring pairs from permissively-licensed Py…
- Seq2seq
- Transformers
- Lora Fine Tuning
Neural Networks for NLP - DesignIntermediateNew
Instrument a Model Monitoring Stack from Scratch
Pick the priority product (recommend the customer-service RAG assistant, around 40k queries/day). Define monitoring signals: input drift (Evidently/NannyML), output quality (LLM…
- Model Monitoring
- Data Drift Detection
- LLM Evaluation
ML Engineering and Production ML - PresentationBeginnerNew
Pitch an LLM Earnings-Call Analyst to an Equity Long-Short Team
Pick 3 publicly available US tech earnings-call transcripts (from a free source like sec.gov filings or company investor-relations pages) and build a retrieval-augmented LLM wor…
- Prompt Engineering
- Retrieval Augmented Generation
- LLM Evaluation
AI and Quantitative Finance - CodeIntermediateNew
Build a Multimodal Generation Pipeline for a Tourism Operator
You receive 40 sample 30-second videos shot by tour guides, the operator's brand voice doc, and SEO keyword lists for EN/PT/ES. Build a pipeline that (1) extracts a representati…
- Multimodal Generation
- Vision Language Models
- LLM Inference
Generative AI Build a verifiable portfolio.
Submissions become evidence. Reviewers with shipping experience score against a rubric; the result becomes a credential anyone can verify.
Why Ewance
- CodeIntermediateNew
Fine-Tune a Diffusion Model for a Sustainable-Fashion Mood-Board Tool
You receive around 1,200 curated images of sustainable garments tagged with silhouette and material. Choose a base diffusion model (Stable Diffusion 1.5/2.1 or SDXL) and apply L…
- Diffusion Models
- Lora Fine Tuning
- Image Generation
Deep Generative Models - ResearchIntermediateNew
QLoRA Fine-Tune for a Customer-Support Domain Assistant
You receive 8,000 anonymized support ticket pairs (question -> agent response), the company's product documentation (around 600 pages), and a strong RAG baseline already running…
- Qlora
- Fine Tuning
- RAG
Open coursework - CodeIntermediateNew
Design Prompt Versioning and Observability for a Coding Assistant
You will (1) design a prompt-registry data model (versions, owners, environments, change log) and implement it in Postgres + a small Python SDK, (2) instrument the assistant to …
- Prompt Versioning
- Observability
- Pii Scrubbing
LLM Application Development - DesignBeginnerNew
Generative AI Content Strategy for a Sustainable Fashion Brand
You must first define EcoWeave's brand voice by analyzing their existing content (provided). Then, design a set of prompts and a workflow (e.g., using ChatGPT or a no-code AI to…
- Prompt Engineering
- Content Strategy
- Brand Voice
Data-Driven Prototyping with AI - CodeIntermediateNew
Ship a Streaming RAG Endpoint with Caching and Fallbacks
You will build a FastAPI service exposing one POST /chat endpoint that (1) streams tokens via Server-Sent Events, (2) caches identical (system_prompt, query, retrieved_context) …
- LLM API Integration
- Streaming
- Response Caching
LLM Application Development - CodeIntermediateNew
Fine-Tune a 3B Open-Weight Model for Customer Support Triage
You receive 40,000 anonymized labelled support tickets across 18 categories. Fine-tune a 3B open-weight model using parameter-efficient fine-tuning (LoRA) for the classification…
- Lora Fine Tuning
- Open Weight Llms
- Classification
Large Language Models
How it works
From brief to credential, in six steps.
Step 01
Browse challenges aligned to your studies.
Step 02
Accept the one that fits your goals.
Step 03
Work through it with AI Copilot guidance.
Step 04
Submit for structured evaluation.
Step 05
Earn a verified credential.
Step 06
Add it to LinkedIn with one click.
Industry teams behind a decade of practitioner briefs
Hiring from this pool?
Sponsor a challenge and meet candidates through actual work.
Industry teams can shape briefs around the skills they hire for, then evaluate students on rubric-scored deliverables — not resumes.



















































































