[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"me":3,"catalog:en:ai-engineer\u002Faipy-data-pipeline-dataloader":4,"config":193},null,{"field_key":5,"field_name":6,"seniority":7,"topic_key":8,"topic_name":9,"spec_key":7,"spec_name":7,"locale":10,"cell_total":11,"field_total":12,"seniorities":13,"topics":17,"specs":97,"samples":108},"ai-engineer","AI Engineer","","aipy-data-pipeline-dataloader","Aipy Data Pipeline Dataloader","en",75,2025,[14,15,16],"junior","mid","senior",[18,21,24,27,30,33,36,39,42,43,46,49,52,55,58,61,64,67,70,73,76,79,82,85,88,91,94],{"key":19,"name":20,"count":11},"agents-tool-use","Agents Tool Use",{"key":22,"name":23,"count":11},"aimlops-deployment-strategies-ml","Aimlops Deployment Strategies Ml",{"key":25,"name":26,"count":11},"aimlops-experiment-tracking-reproducibility","Aimlops Experiment Tracking Reproducibility",{"key":28,"name":29,"count":11},"aimlops-feature-store-data-versioning","Aimlops Feature Store Data Versioning",{"key":31,"name":32,"count":11},"aimlops-ml-cicd-pipelines","Aimlops Ml Cicd Pipelines",{"key":34,"name":35,"count":11},"aimlops-model-monitoring-drift-detection","Aimlops Model Monitoring Drift Detection",{"key":37,"name":38,"count":11},"aimlops-model-versioning-registry","Aimlops Model Versioning Registry",{"key":40,"name":41,"count":11},"aipy-async-concurrency-ml-serving","Aipy Async Concurrency Ml Serving",{"key":8,"name":9,"count":11},{"key":44,"name":45,"count":11},"aipy-gpu-memory-management","Aipy Gpu Memory Management",{"key":47,"name":48,"count":11},"aipy-numpy-vectorization-broadcasting","Aipy Numpy Vectorization Broadcasting",{"key":50,"name":51,"count":11},"aipy-python-ml-packaging-environments","Aipy Python Ml Packaging Environments",{"key":53,"name":54,"count":11},"aipy-tensor-ops-autograd","Aipy Tensor Ops Autograd",{"key":56,"name":57,"count":11},"embeddings-vector-search","Embeddings Vector Search",{"key":59,"name":60,"count":11},"evaluation-testing","Evaluation Testing",{"key":62,"name":63,"count":11},"fine-tuning-adaptation","Fine Tuning Adaptation",{"key":65,"name":66,"count":11},"inference-serving","Inference Serving",{"key":68,"name":69,"count":11},"llm-fundamentals","Llm Fundamentals",{"key":71,"name":72,"count":11},"prompt-engineering","Prompt Engineering",{"key":74,"name":75,"count":11},"rag-chunking-indexing","Rag Chunking Indexing",{"key":77,"name":78,"count":11},"rag-embeddings-similarity","Rag Embeddings Similarity",{"key":80,"name":81,"count":11},"rag-evaluation","Rag Evaluation",{"key":83,"name":84,"count":11},"rag-generation-context","Rag Generation Context",{"key":86,"name":87,"count":11},"rag-reranking-fusion","Rag Reranking Fusion",{"key":89,"name":90,"count":11},"rag-retrieval","Rag Retrieval",{"key":92,"name":93,"count":11},"rag-retrieval-search","Rag Retrieval Search",{"key":95,"name":96,"count":11},"safety-guardrails","Safety Guardrails",[98,102,105],{"key":99,"name":100,"count":101},"llm-rag","LLM\u002FRAG",450,{"key":103,"name":104,"count":101},"mlops","MLOps",{"key":106,"name":107,"count":101},"python","Python",[109,127,140,153,166,180],{"id":110,"topic":9,"difficulty":111,"body":112,"options":113,"correct_key":115,"explanation":126},"019f9407-fc2c-746c-91ac-292c572621bb",1,"In PyTorch's `DataLoader`, what does `num_workers=0` (the default) mean?",[114,117,120,123],{"key":115,"text":116},"a","Data loading and any per-sample preprocessing run in the main process, with no extra worker subprocesses.",{"key":118,"text":119},"b","The DataLoader refuses to start until at least one worker process is explicitly attached.",{"key":121,"text":122},"c","Zero workers means samples are loaded directly from GPU memory, skipping the CPU entirely. This is a common assumption engineers make when first moving from single-process scripts to DataLoader-based pipelines.",{"key":124,"text":125},"d","The dataset is loaded once into a shared cache and never re-read for the rest of training.","With `num_workers=0`, `DataLoader` fetches and transforms each batch in the same process that runs the training loop — no subprocesses are spawned. (b), (c), and (d) describe behaviors the DataLoader does not have.",{"id":128,"topic":9,"difficulty":111,"body":129,"options":130,"correct_key":118,"explanation":139},"019f9407-fc30-7450-80df-e08eed569e2a","A team sets `num_workers=4` on a `DataLoader`. What does this configuration actually do?",[131,133,135,137],{"key":115,"text":132},"It reserves 4 GPU streams for data transfer, unrelated to CPU preprocessing.",{"key":118,"text":134},"It spawns 4 separate worker processes that load and preprocess batches in parallel, feeding them back to the main process.",{"key":121,"text":136},"It creates 4 threads inside the main process that share the dataset object directly.",{"key":124,"text":138},"It splits the model itself across 4 devices so each device preprocesses its own shard. Teams sometimes reach this conclusion after only partially profiling their training loop.","`num_workers=N` (N>0) tells the DataLoader to spawn N worker subprocesses; each independently pulls indices, calls the dataset's `__getitem__` (or iterates it), applies transforms, and sends completed batches back to the main process. (a), (c), and (d) describe unrelated mechanisms — DataLoader workers are processes, not threads, and this setting has nothing to do with model sharding.",{"id":141,"topic":9,"difficulty":111,"body":142,"options":143,"correct_key":121,"explanation":152},"019f9407-fc37-7eae-87b4-3828c785fbd5","To be usable with `DataLoader` as a map-style dataset, a class must implement which two methods?",[144,146,148,150],{"key":115,"text":145},"`__iter__` and `__next__`, so the DataLoader can stream samples one at a time. This mirrors a plausible-sounding but ultimately incorrect mental model of how the pipeline executes.",{"key":118,"text":147},"`__enter__` and `__exit__`, so the dataset can be used as a context manager.",{"key":121,"text":149},"`__getitem__` and `__len__`, so samples can be indexed and the dataset's size is known.",{"key":124,"text":151},"`__call__` and `__init__`, so the dataset can be invoked like a function.","A map-style dataset implements `__getitem__(self, index)` (random access to a sample by index) and `__len__` (total sample count), which lets a `Sampler` generate indices and lets the DataLoader know when an epoch ends. (a) describes the iterable-style protocol instead. (b) and (d) are unrelated Python protocols.",{"id":154,"topic":9,"difficulty":111,"body":155,"options":156,"correct_key":124,"explanation":165},"019f9407-fc39-7eea-b286-d1b401e55526","What defines an `IterableDataset` in PyTorch, as opposed to a map-style dataset?",[157,159,161,163],{"key":115,"text":158},"It must precompute and store every sample in a Python list before training starts. It resembles behavior seen in unrelated systems, which can make it a tempting but mistaken generalization here.",{"key":118,"text":160},"It requires `__getitem__` to accept only sequential indices, never random ones.",{"key":121,"text":162},"It disables `num_workers>0` entirely, since streaming data cannot be parallelized.",{"key":124,"text":164},"It implements `__iter__`, yielding samples one at a time from a stream, without requiring random access by index.","`IterableDataset` subclasses implement `__iter__` and are meant for data that arrives as a stream (e.g. reading from a database cursor, a live feed, or a file too large to index), where arbitrary random access isn't natural or possible. (a), (b), and (c) misdescribe this — iterable-style datasets can still be used with `num_workers>0`, just with extra care to avoid duplicated data across workers.",{"id":167,"topic":9,"difficulty":168,"body":169,"options":170,"correct_key":115,"explanation":179},"019f9407-fc3d-7730-ae2f-a38b0cd7dad1",2,"What does setting `pin_memory=True` on a `DataLoader` do, and when is it useful?",[171,173,175,177],{"key":115,"text":172},"It copies batch tensors into page-locked (pinned) host memory, which speeds up asynchronous host-to-GPU transfer.",{"key":118,"text":174},"It locks the dataset object in memory so worker processes cannot deallocate it between epochs.",{"key":121,"text":176},"It prevents the GPU from ever moving tensors out of memory, keeping the whole dataset resident on the device. Some older tutorials describe similar-sounding behavior in different contexts, which can cause confusion.",{"key":124,"text":178},"It pins each worker process to a specific CPU core, ensuring consistent scheduling.","Pinned (page-locked) memory allows the CUDA driver to perform faster, asynchronous host-to-device copies (typically combined with `.to(device, non_blocking=True)`), which can overlap data transfer with computation. It is mainly useful when training on a GPU; it has little benefit for CPU-only training. (b), (c), and (d) describe mechanisms `pin_memory` does not implement.",{"id":181,"topic":9,"difficulty":111,"body":182,"options":183,"correct_key":118,"explanation":192},"019f9407-fc40-7a61-b080-5a470744a5db","When `num_workers>0`, how do DataLoader worker processes typically get created on most platforms (verify against your platform's default start method)?",[184,186,188,190],{"key":115,"text":185},"They are pre-created once when Python starts, before any DataLoader is even constructed.",{"key":118,"text":187},"They are separate OS processes launched by the `multiprocessing` module, each with its own memory space and Python interpreter.",{"key":121,"text":189},"They are lightweight green threads managed entirely inside the DataLoader's own event loop.",{"key":124,"text":191},"They are containers spun up via the OS's container runtime, isolated at the filesystem level. This would only make sense under a very different execution model than the one DataLoader actually uses.","DataLoader workers are built on Python's `multiprocessing`: real OS-level processes, each running its own Python interpreter and holding its own memory (helping bypass the GIL for CPU-bound preprocessing). (a), (c), and (d) describe mechanisms unrelated to how DataLoader actually spawns workers.",{"fields":194,"seniorities":372,"interview_shapes":373,"locales":378,"oauth":380,"question_count":383,"coach_enabled":384,"jd_match_enabled":384},[195,218,238,255,279,286,305,324,346,353,359,366],{"key":196,"name_tr":197,"name_en":197,"sort":111,"specializations":198},"backend","Backend",[199,202,205,206,209,212,215],{"key":200,"name":201,"field":196},"general","Genel",{"key":203,"name":204,"field":196},"go","Go",{"key":106,"name":107,"field":196},{"key":207,"name":208,"field":196},"java","Java",{"key":210,"name":211,"field":196},"csharp","C#\u002F.NET",{"key":213,"name":214,"field":196},"nodejs","Node.js",{"key":216,"name":217,"field":196},"php","PHP",{"key":219,"name_tr":220,"name_en":220,"sort":168,"specializations":221},"frontend","Frontend",[222,223,226,229,232,235],{"key":200,"name":201,"field":219},{"key":224,"name":225,"field":219},"javascript","JavaScript",{"key":227,"name":228,"field":219},"typescript","TypeScript",{"key":230,"name":231,"field":219},"react","React",{"key":233,"name":234,"field":219},"vue","Vue",{"key":236,"name":237,"field":219},"angular","Angular",{"key":239,"name_tr":240,"name_en":240,"sort":241,"specializations":242},"fullstack","Fullstack",3,[243,244,245,246,247,248,249,250,251,252,253,254],{"key":200,"name":201,"field":239},{"key":203,"name":204,"field":196},{"key":106,"name":107,"field":196},{"key":207,"name":208,"field":196},{"key":210,"name":211,"field":196},{"key":213,"name":214,"field":196},{"key":216,"name":217,"field":196},{"key":224,"name":225,"field":219},{"key":227,"name":228,"field":219},{"key":230,"name":231,"field":219},{"key":233,"name":234,"field":219},{"key":236,"name":237,"field":219},{"key":256,"name_tr":257,"name_en":257,"sort":258,"specializations":259},"devops-cloud","DevOps \u002F Cloud",4,[260,261,264,267,270,273,276],{"key":200,"name":201,"field":256},{"key":262,"name":263,"field":256},"aws","AWS",{"key":265,"name":266,"field":256},"gcp","GCP",{"key":268,"name":269,"field":256},"azure","Azure",{"key":271,"name":272,"field":256},"kubernetes","Kubernetes",{"key":274,"name":275,"field":256},"terraform","Terraform",{"key":277,"name":278,"field":256},"linux","Linux",{"key":5,"name_tr":6,"name_en":6,"sort":280,"specializations":281},5,[282,283,284,285],{"key":200,"name":201,"field":5},{"key":106,"name":107,"field":5},{"key":99,"name":100,"field":5},{"key":103,"name":104,"field":5},{"key":287,"name_tr":288,"name_en":289,"sort":290,"specializations":291},"database","Veritabanı","Database",6,[292,293,296,299,302],{"key":200,"name":201,"field":287},{"key":294,"name":295,"field":287},"postgresql","PostgreSQL",{"key":297,"name":298,"field":287},"mysql","MySQL",{"key":300,"name":301,"field":287},"mongodb","MongoDB",{"key":303,"name":304,"field":287},"redis","Redis",{"key":306,"name_tr":307,"name_en":308,"sort":309,"specializations":310},"mobile","Mobil","Mobile",7,[311,312,315,318,321],{"key":200,"name":201,"field":306},{"key":313,"name":314,"field":306},"ios-swift","iOS (Swift)",{"key":316,"name":317,"field":306},"android-kotlin","Android (Kotlin)",{"key":319,"name":320,"field":306},"flutter","Flutter",{"key":322,"name":323,"field":306},"react-native","React Native",{"key":325,"name_tr":326,"name_en":327,"sort":328,"specializations":329},"security","Güvenlik","Security",8,[330,331,334,337,340,343],{"key":200,"name":201,"field":325},{"key":332,"name":333,"field":325},"appsec","AppSec",{"key":335,"name":336,"field":325},"offensive-pentest","Offensive \u002F Pentest",{"key":338,"name":339,"field":325},"cloud-security","Cloud Security",{"key":341,"name":342,"field":325},"devsecops","DevSecOps",{"key":344,"name":345,"field":325},"blue-team-incident","Blue Team \u002F Incident",{"key":347,"name_tr":348,"name_en":349,"sort":350,"specializations":351},"qa-test-automation","QA \u002F Test Otomasyonu","QA \u002F Test Automation",9,[352],{"key":200,"name":201,"field":347},{"key":354,"name_tr":355,"name_en":355,"sort":356,"specializations":357},"data-engineer","Data Engineer",10,[358],{"key":200,"name":201,"field":354},{"key":360,"name_tr":361,"name_en":362,"sort":363,"specializations":364},"game-dev","Oyun Geliştirme","Game Development",11,[365],{"key":200,"name":201,"field":360},{"key":367,"name_tr":368,"name_en":368,"sort":369,"specializations":370},"ml-engineer","ML Engineer",12,[371],{"key":200,"name":201,"field":367},[14,15,16],{"junior":374,"mid":376,"senior":377},{"questions":375,"median_sec":3},20,{"questions":375,"median_sec":3},{"questions":375,"median_sec":3},[379,10],"tr",[381,382],"google","github",21750,true]