lovefromatx

Obviously compensation is an issue but an experienced engineer has a very little incentive to find letters of recommendation, personal statement and wait for really long hiring cycles and horrendous ATS. The position ultimately puts a ceiling in career progression as well because they might not have a Phd and may never be considered qualified for a Managerial Position later on either.

Different context but Buffett's quote “If a cop follows you for 500 miles, you’re going to get a ticket,” applies here. If you are a criminal you don't violate only one law. You tend to violate multiple laws and at some point you are going to be sloppy.

word2vec is useful when one wants to build a machine learning based system. It allows you to get away with a really small matrix [number of documents,~25-1000]. This really makes ML feasible. Another advantage is preserving context. A vector for car and vehicle are closely aligned.

Problem when implementing a vector based search engine system is that your recall is going to be really high. You will potentially get a lot of marginally related results with your query.

My recommendation will be to implement a tf idf based system. You could enhance your queries by also enriching them with synonyms as well. You could find synonyms by using something like LDA, get a topic model and use the words add the words from that topic in the query.