Reinforcement Learning Engineer
Budget: ₹37,500 – ₹75,000 INR
Objective: Build an RLHF(Reinforcement Learning from Human Feedback) model to shortlist resumes.
The flow:
- The front end sends a list of ingested resumes to the backend. (in pdf/docx/url).
- Preprocess the data.
- Pass the content to the model and generate an initial recommendation based on a model built with transfer learning(BERT or Roberta).
- Ask for feedback and retrain the model, and make optimization so we don’t have to retrain the entire model every time(Save weights).
The flow:
- The front end sends a list of ingested resumes to the backend. (in pdf/docx/url).
- Preprocess the data.
- Pass the content to the model and generate an initial recommendation based on a model built with transfer learning(BERT or Roberta).
- Ask for feedback and retrain the model, and make optimization so we don’t have to retrain the entire model every time(Save weights).