Summary
At ZipRecruiter, there are plenty of opportunities for innovation within a vast universe of data, including over a billion archived job postings, tens of millions of dynamic job seekers, and countless impression and click events. This role offers the chance to craft new, data-driven features that impact the lives of millions by connecting them to their dream jobs. The team is tackling exciting challenges, such as developing a system to predict salaries for new job postings using a training set of job postings and known salaries. The work involves an immersive dive into data—gathering, cleaning, analyzing, and extracting meaningful insights.
Key Focuses
- Design, develop, and maintain machine learning models and algorithms to solve complex business problems
- Identify patterns, trends, and anomalies in the data, and visualize insights using appropriate tools
- Assess the performance of machine learning models using appropriate metrics, validation techniques, and testing datasets
- Discover opportunities to optimize models by fine-tuning hyperparameters, feature selection, or employing regularization techniques to improve accuracy, performance, and scalability
Minimum Qualifications
- 3+ years of professional software development experience with a focus in machine learning
- Deep experience in machine learning algorithms, techniques, and best practices
- Comprehensive computer science fundamentals in coding, object-oriented programming, data structures, and algorithms
Preferred Qualifications
- 5+ years of professional software development experience with a focus in machine learning
- BS/MS/PhD in Mathematics, Computer Science, Physics, related technical field or equivalent practical experience
- Strong knowledge of machine learning algorithms (e.g., linear regression, SVM, decision trees, neural networks, clustering, etc.) and best practices
- Experience with machine learning algorithms and frameworks, such as TensorFlow, PyTorch, or scikit-learn
- Experience with deep learning architectures and techniques, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), and Generative Adversarial Networks (GANs)
- Background with NLP techniques and tools, such as tokenization, stemming, lemmatization, sentiment analysis, and named entity recognition, and libraries like NLTK, SpaCy, or BERT