Bijay Gurung
Applied NLP Engineer at deepset
Freiburg im Breisgau, Baden-Württemberg, Germany
Summary
🤩
Rockstar🎓
Top SchoolBijay Gurung is an Applied NLP Engineer with 11 years of experience building production ML systems across recommendation engines, time series forecasting, and a wide range of NLP tasks. Based in Freiburg, he has driven measurable business impact—such as a 6% revenue uplift on a cross-sell recommender and reduced forecasting loss versus domain experts—while contributing to open-source AI tooling. At deepset he improved retrieval for LLM applications by enhancing Haystack’s EmbeddingRetriever with advanced training losses and a JsonConverter, highlighting a focus on retrieval-augmented workflows. He combines strong engineering craft (TensorFlow/Keras, scikit-learn, spaCy) with hands-on ML ops and pedagogy, having co-led industry training programs and university courses. Curious and prolific, he publishes both code and prose and treats learning as a core practice that shapes pragmatic, production-ready solutions.
11 years of coding experience
7 years of employment as a software developer
Master's degree Informatik/Computer Science, Master's degree Informatik/Computer Science at The University of FreiburgBachelor’s Degree Computer Engineering, Bachelor’s Degree Computer Engineering at IOE, PulchowkHigh School Science, High School Science at Reliance International Academy
English, Nepali
Stackoverflow
31reputation
39kreached
1answer
3questions
Github Skills (13)
transformers10
pytorch10
machine-learning10
retrieval-augmented-generation10
nlp10
large-language-models10
sentence-transformers10
python10
generative-ai10
ai10
natural-language-processing10
question-answering9
json9
Programming languages (5)
Github contributions (5)
deepset-ai/haystack
Aug 2022 - Sep 2022
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
Role in this project:
ML Engineer
ML EngineerContributions:25 reviews, 3 commits, 9 PRs in 1 month
Contributions summary:Bijay primarily focused on enhancing the `EmbeddingRetriever` component within the Haystack framework. Their contributions include adding options to use the MultipleNegativesRankingLoss for training with sentence-transformers, modifying the underlying losses, and incorporating a `JsonConverter` node. The user's work demonstrates a clear focus on improving retrieval methods and data processing capabilities within the context of building LLM applications.
aillmmultimodalorchestration-frameworksemantic-search
bglearning/ZeroneScholar2016
Nov 2016 - Nov 2016
Contributions:14 commits, 2 PRs, 5 pushes in 15 days
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.