Benchmarking
If you like applying Benchmarking, every challenge here gives you a chance to practice it on a real industry brief.
- CodeAdvancedNew
Design Error Recovery for a Friendly Compiler
Read the existing parser (recursive-descent, in Rust). Design and implement a panic-mode error recovery strategy with synchronization tokens (statement boundary, end of block, s…
- Error Recovery
- Recursive Descent Parsing
- Diagnostic Design
Compiler Construction - AnalysisAdvancedNew
Cost-Optimize a Misshapen Kubernetes Cluster
Receive 30 days of cluster metrics (Prometheus + AWS Cost Explorer exports), Helm releases, and PodDisruptionBudgets per namespace. Profile: identify the top 3 cost drivers (lik…
- Kubernetes
- Cost Optimization
- Aws
Cloud Computing - AnalysisAdvancedNew
GPU Roofline Model Study for a Computer Vision Inference Workload
Construct empirical roofline plots for the current GPU (A100-class) and next-gen GPU (H100-class) using vendor-published peak FLOPs and measured peak memory bandwidth. Profile t…
- Gpu Architecture
- Roofline Model
- Performance Modeling
Advanced Computer Architecture - AnalysisAdvancedNew
Benchmark NPUs for an Autonomous Forklift Vision Stack
You receive ONNX exports of the 3 production models, a labeled validation set of 2,000 forklift-camera frames, and developer-kit access to three NPU candidates (anonymized as NP…
- Edge Inference
- Npu Benchmarking
- Onnx
Edge ML and On-Device Machine Learning Develop in-demand professional skills.
Each challenge names the skills it strengthens. Over time, your profile fills with the competences a hiring manager would actually look for.
Why Ewance
- AnalysisAdvancedNew
Audit BLEU vs. COMET on a Multilingual Customer-Support Corpus
You receive 600 source-translation-reference triples covering 6 languages (EN as source; ES/FR/DE/JA/PT-BR/HI as targets), each scored on adequacy and fluency (1-6) by 3 profess…
- Mt Evaluation
- Neural Mt
- Statistical Analysis
Machine Translation - CodeAdvancedNew
Tune a Multicore Pipeline with NUMA-Aware Sharding
Receive the current worker (Rust, around 8,000 lines, uses rayon for its parallelism), the host (2-socket AMD EPYC 9354, 64 cores total, 384GB DDR5), and a benchmark query workl…
- Parallel Performance
- Numa
- Rust
Advanced Concurrency and Parallel Computing - AnalysisAdvancedNew
Benchmark Visual SLAM Stacks for an Indoor Delivery Robot
You receive 8 indoor rosbag recordings (about 90 minutes total) captured by the robot's stereo camera + Inertial Measurement Unit (IMU) plus ground-truth trajectories from an ex…
- Visual Slam
- Sensor Fusion
- Trajectory Evaluation
Robot Perception and Autonomy - AnalysisAdvancedNew
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 - Browse challenges
Explore role
Strategy Analyst
Frame the business question, model the options, build the recommendation. From market sizing to competitive analysis, this role is where strategy consulting meets in-house decision-making.
- AnalysisAdvancedNew
Spectral Clustering for Customer Segmentation at a SaaS
Receive a 12,000 customer × 220 feature usage matrix (counts per feature per week, averaged over 12 weeks). Construct a similarity graph (k-nearest-neighbors with k=15, Gaussian…
- Spectral Methods
- Linear Algebra
- Algorithm Analysis
Advanced Algorithms - CodeAdvancedNew
Hierarchical Plans for an Aerospace Maintenance Crew Scheduler
You receive a synthetic week of 80 work orders with hierarchical decompositions, technician certifications, and shared-tool constraints. Implement an HTN planner (PyHOP or HDDL …
- Htn Planning
- Domain Modeling
- Constraint Handling
Automated Planning - CodeAdvancedNew
Build a Variant-Calling Pipeline for a Genomics SaaS
Stand up a Nextflow pipeline covering: read trimming, BWA-MEM alignment, duplicate marking, base-quality-score recalibration, GATK HaplotypeCaller variant calling, and variant f…
- Bioinformatics
- Variant Calling
- Workflow Orchestration
Computational Biology and Health Informatics - CodeAdvancedNew
Solve a Vehicle-Routing Problem with Tabu Search
You receive a week of anonymized daily VRPTW instances (around 800 orders per day, 120 vehicles, hard delivery windows). Implement tabu search with: a route-insertion constructi…
- Tabu Search
- Metaheuristics
- Vehicle Routing
Evolutionary Computation and Metaheuristic Search Get recognized by recruiters and employers.
Credentials are blockchain-anchored via LearnCoin — tamper-evident, portable, link-shareable on LinkedIn and beyond.
Why Ewance
- CodeAdvancedNew
Design a Lock-Free Concurrent Queue for an Event Bus
Implement an MPSC (multi-producer single-consumer) ring-buffer queue in Go using atomic operations only — no mutexes. Prove correctness with the Go race detector across 8 produc…
- Concurrent Data Structures
- Lock Free Programming
- Go
Data Structures - CodeAdvancedNew
Implement a Persistent Immutable List for a Collaborative-Editing Startup
Implement in Python (or TypeScript / Kotlin). Build a persistent immutable list with operations: get, set, append, pop, slice, concat. Use structural sharing (32-way vector trie…
- Data Abstraction
- Recursion
- Persistent Data Structures
Programming Abstractions - CodeAdvancedNew
Plan Warehouse Pick Routes with a Classical Planner
You receive a stylized warehouse map (aisle graph), 30 sample shifts of pick tasks, and the current heuristic's outputs. Write a PDDL domain + problem generator, solve with at l…
- Pddl Modeling
- State Space Search
- Classical Planning
Automated Planning - ResearchAdvancedNew
Planning Under Uncertainty for a Last-Mile Delivery Fleet
Build a simulator of the 50-block area with stochastic travel times conditioned on weather and time-of-day. Implement value iteration (for a small state space), MCTS (Monte Carl…
- Planning Under Uncertainty
- Markov Decision Processes
- Monte Carlo Tree Search
Automated Planning - AnalysisAdvancedNew
Evaluate OS-Level Containment for a Multi-Tenant Edge Platform
Set up reproducible environments for gVisor, Firecracker, and Wasmtime on identical hardware (4 vCPU, 8 GB RAM). Run the platform's 4 workload archetypes (anonymized): API proxy…
- Containment
- Virtualization
- Wasm
Advanced Operating Systems - AnalysisAdvancedNew
Optimize a Slow Trino Query Over a Petabyte Warehouse
Receive the slow SQL query (around 600 lines), the Trino EXPLAIN ANALYZE output, the underlying Iceberg table schemas (partition specs, sort orders), and 30 days of execution me…
- Trino
- Sql Optimization
- Iceberg
Big Data and Data-Intensive Systems - AnalysisAdvancedNew
Compare Stereo Depth Methods for a Drone Inspection Startup
You receive 500 calibrated stereo pairs from a turbine inspection plus sparse LiDAR ground truth on each pair. Implement (or wrap) three depth estimators: OpenCV Semi-Global Mat…
- Stereo Depth Estimation
- Multi View Geometry
- Model Evaluation
3D Vision and Multi-View Geometry - CodeAdvancedNew
Implement Bulk Synchronous Parallel PageRank on a 1.5B-Edge Graph
Choose either Apache Spark + GraphX (Pregel API) or a vanilla MPI + C++ implementation. Run 25 iterations of PageRank on the 1.5B-edge graph (graph file format provided: CSR par…
- Parallel Algorithms
- Bsp
- Graph Algorithms
Parallel and Distributed Algorithms - AnalysisAdvancedNew
Cost-Optimize a Large-Scale Spark Job for an Ad-Tech Platform
You receive the Spark job source (PySpark), the EMR cluster config, and 5 nights of job-history JSON. Profile the job with the Spark UI + EMR metrics, identify the top 3 cost dr…
- Spark Optimization
- Cloud Services
- Cost Engineering
Cloud Computing for Data and ML - CodeAdvancedNew
Detect Atrial Fibrillation from Wearable Heart-Rate Data
Build a Python pipeline that ingests raw PPG + accelerometer at 100Hz, applies motion-artifact rejection using the accelerometer channel, detects beats, computes RR-interval irr…
- Health Sensing
- Signal Processing
- Biomedical Signals
Computational Biology and Health Informatics - AnalysisAdvancedNew
Benchmark Approximate Nearest-Neighbor Indexes for a Code-Search Startup
You receive a 5 M-vector sample (768-dim, float32) and a 1,000-query labeled benchmark with ground-truth top-50 neighbors per query. Index the same sample in Chroma (HNSW), Qdra…
- Ann Indexes
- Hnsw
- Benchmarking
Vector Databases and Embeddings - CodeAdvancedNew
Restore Smartphone Low-Light Photos for a Consumer AI App
You receive 200 paired low-light / well-lit phone photos plus 1,000 unpaired low-light photos. Build a pipeline that combines a learned denoiser (e.g. a small DnCNN-style model …
- Image Restoration
- Denoising
- Tone Mapping
Image Processing and Computational Imaging
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.