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.
- CodeBeginnerNew
Build a Math Intelligent-Tutoring Assistant for High Schoolers
You receive: a curated set of 40 algebra problems with worked solutions, the company's pedagogy rubric ('hint, don't reveal' principle), and a baseline 'just answer' chatbot for…
- Intelligent Tutoring
- Prompt Engineering
- LLM Agents
AI in Education and Learning Analytics - CodeIntermediateNew
Wire a Knowledge Graph into a Pharma RAG Assistant
You receive: 100 internal benchmark questions with reference answers; a 50,000-document anonymized RAG index; a curated drug-target-disease KG (~80,000 triples) loaded into a tr…
- Kg Grounded RAG
- Sparql
- Entity Linking
Knowledge Graphs and Semantic Web - CodeIntermediateNew
Build a Tool-Calling Agent for an Internal Reporting Bot
You will implement the agent in either LangChain or LlamaIndex (your choice; defend it in the readme). Wire 4 tools: (1) read-only SQL on a sample warehouse, (2) a mocked BI met…
- Agent Orchestration
- Tool Calling
- Langchain Or Llamaindex
LLM Application Development - DesignIntermediateNew
Design a Continuous Eval Pipeline for an Enterprise RAG Product
Design (and partially build) a continuous-eval pipeline for a RAG system: (1) a structured eval set with at least 50 queries grouped by query class; (2) automated scoring (LLM-a…
- Continuous Evaluation
- LLM Evaluation
- Retrieval Augmented Generation
AI Measurement and Evaluation 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
- 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
Computational Semantics - 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
Instruction-Tune a Small Model for an Edtech Tutor
You receive a 1.5B base model (e.g., SmolLM-1.7B or Qwen-1.8B), permission to use 2 hours of a rented A100, and a curated seed of around 5,000 math-tutoring dialogues. Augment w…
- Instruction Tuning
- Supervised Fine Tuning
- Dataset Curation
Fine-Tuning Large Language Models - DesignBeginnerNew
Design an Automated Essay-Feedback System
You receive 20 anonymized middle-school essays scored by 2 human teachers on a 4-dimension rubric (structure, evidence, voice, mechanics). Design an LLM-based feedback system th…
- Automated Assessment
- Rubric Design
- Prompt Engineering
AI in Education and Learning Analytics - 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 - CodeIntermediateNew
Build a BM25 + Embeddings Hybrid Search for a Legal-Tech Document Portal
Stand up an OpenSearch cluster with BM25 indexing on the 2.4M-document corpus. Generate dense embeddings (you choose the model; justify cost and quality trade-offs) and index th…
- Information Retrieval
- Bm25
- Vector Search
Data Mining and Information Retrieval - ResearchSeniorNew
Multi-Tenant Vector Isolation for a B2B Knowledge Assistant
Build a small proof-of-concept in your chosen vector store (Pinecone or Qdrant — pick one and justify) that supports 10 simulated tenants with 1,000 vectors each. Implement the …
- Multi Tenant Isolation
- Vector Databases
- Threat Modeling
Vector Databases and Embeddings - 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
Data-Driven Prototyping with 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
- ResearchSeniorNew
Plan a Parameter-Efficient Fine-Tuning Strategy for a Big-Tech AI Lab
You will produce (1) a 6-page survey of four PEFT methods (LoRA, adapters, prefix tuning, IA3) with their strengths, weaknesses, and parameter footprints, (2) a one-page decisio…
- Parameter Efficient Fine Tuning
- Transfer Learning
- Fine Tuning
Meta-Learning, Transfer Learning, and Multi-Task Learning - AnalysisIntermediateNew
Catastrophic-Forgetting Audit on a Domain Fine-Tune
You receive the fine-tuned 7B chemistry model and its base, plus a benchmark basket (MMLU subset, GSM8K, IFEval, a small instruction-following set). Run all 4 benchmarks on both…
- Catastrophic Forgetting
- LLM Evaluation
- Fine Tuning
Fine-Tuning Large Language Models - AnalysisBeginnerNew
Cost-Optimize an Embedding Pipeline for a Customer Support Knowledge Base
You receive: (a) the current pipeline (full re-embed on any article change, OpenAI text-embedding-3-large, 3,072 dims) with one month of cost logs, (b) a sample of 5,000 article…
- Embedding Models
- Cost Optimization
- Change Detection
Vector Databases and Embeddings - 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
Fine-Tuning Large Language Models - CodeBeginnerNew
Prototype a Multimodal Visual-Question-Answering Demo
You will use a small open-source vision-language model (e.g., LLaVA-1.5-7B or PaliGemma) and prompt-engineer it for the warehouse-VQA task. Build a Gradio web demo. Construct a …
- Vision Language Models
- Multimodal Perception
- Prompt Engineering
Machine Perception - DesignBeginnerNew
Build the PRD for an Internal RAG Knowledge Assistant
You receive: a description of the CS workflows (post-sale onboarding, escalation, renewal), an inventory of internal knowledge sources (Notion, Salesforce, Zendesk macros, 3 pro…
- Product Management
- Retrieval Augmented Generation
- Evaluation Design
AI for Business and AI Product Management
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.



















































































