Module Lead (Search and Match)

BOLD is seeking for senior professional who will combine analytical skills and business knowledge to deliver key insights to our Product and Management teams. You’ll help drive product development using our vast user data sets to enhance our current products and to help us find inferences and relationships in this data to build new products – More towards the role required ABOUT THIS TEAM BOLD Platform services team design, creates, manage and maintains the highly scalable and distributed services for the wider use of web and mobile product applications/portals/websites. The current list of services is based on Microservices architecture whose domain ranges from visitor tracking, User profiles, authentication, content and payments. Platform team uses state of the art modern technologies like .Net framework, Python, Java, SQL Server, My SQL, Graph DB, SOLR, and a lot of other tools & technologies serving millions of users with hundreds of million transactions everyday through a scalable and fault tolerant architecture. WHAT YOU’LL DO Demonstrate ability to work on data science projects involving NLP, large language models, predictive modelling, statistical analysis, vector space modelling, machine learning etc. Leverage our rich data sets of user data to perform research, develop models and create data products with our Development & Product teams Develop novel and scalable data systems in cooperation with our system architects that leverage datasets using machine learning techniques to enhance the user experience Collaborates effectively with cross functional teams to deliver end-to-end products & features. Demonstrates ability to multi-task and re-prioritize responsibilities based on changing requirements. Estimates efforts, identify risks, devises and meets project schedules. Runs review meetings effectively and drive the closure of all open issues on time Mentors/coaches data scientists to facilitate their development and provide technical leadership to them. Rises above detail to see broader issues and implications for whole product/team. WHAT YOU’LL NEED Knowledge and experience using statistical and machine learning algorithms including regression, instance-based learning, decision trees, Bayesian statistics, clustering, neural networks, deep learning, ensemble methods Expert knowledge in Python.  Practical LLM/RAG experience for search quality  such as  query understanding, semantic retrieval, reranker design. Experience with Solr/OpenSearch/Elasticsearch . Experience with frameworks that optimizes prompt engineering (langChain/crewai/etc) Experience with embedding & vector search  Experience in using large language models. Experience in feature selection, building and optimising classifiers. Experience working with backend technologies such as Flask/ Gunicorn etc. Experience on working with open source library such Spacy,NLTK,Gensim etc  Experience on working with deep-learning library such as Tensor flow, Pytorch etc