IGC team will work

Summary

ClifyX is a company seeking to enhance search relevance and personalization through machine learning. The role involves designing and implementing machine learning models, analyzing search queries, and optimizing search engine configurations to improve user experience and product discovery.

Responsibilities

• Design, train, and evaluate ranking models (learning-to-rank, neural networks, embedding-based approaches) to optimize search relevance and personalization
• Analyze search query logs, evaluate user behavior data to identify opportunities for relevance improvements and inform ranking strategies
• Develop and engineer features from search, product, and user data to power ML models and improve ranking performance
• Implement semantic search for improved product discovery across chemistry and life science domains
• Optimize Elasticsearch/Lucene configurations, including tokenization, stemming, query parsing, and lexical search algorithms (BM25) to work in concert with ML models
• Build and maintain end-to-end ML pipelines, including data preprocessing, feature engineering, model training, evaluation, and deployment using MLOps best practices
• Develop personalized ranking strategies that adapt to user segments, query intent, and business objectives; integrate collaborative filtering and content-based approaches
• Monitor search and ML model performance metrics in production; identify drift and continuously improve models based on new data and domain insights

Skills

• Bachelor's degree in Computer Science, Engineering, Data Science, or a related quantitative field
• 3 years of hands-on experience in machine learning, data science, search relevance, or ranking systems
• Proven expertise in Python and ML frameworks (MLFlow, TensorFlow, PyTorch, Scikit-learn or equivalent)
• Strong background in statistical analysis, data exploration, and working with large-scale datasets
• Experience with feature engineering, data preprocessing, and data manipulation libraries (Pandas, NumPy, Spark)
• Demonstrated experience building or working with ranking models (learning-to-rank, neural ranking, or similar)
• Experience with semantic search, embedding, or dense retrieval methods
• Deep understanding of search engines (Elasticsearch, Solr, OpenSearch), lexical search algorithms (BM25), information retrieval concepts, search relevance tuning, tokenization, stemming, and query parsing
• Experience with MLOps practices and tools (model versioning, experiment tracking, pipeline orchestration)
• Proficiency in SQL and querying large datasets
• Strong problem-solving and analytical skills with the ability to think critically about complex search and ranking problems
• Excellent communication skills; ability to explain ML and search concepts to both technical and non-technical stakeholders
• Ability to collaborate with cross-functional teams
• Search Query Analysis: Analyze search query logs, evaluate user behavior data to identify opportunities for relevance improvements and inform ranking strategies
• Experience in training & fine tuning the models
• Experience with large language models (LLMs) or prompt engineering
• Experience with semantic indexing and dense vector search (e.g., vector databases)
• Experience in Search Metrics evolution
• Familiarity with data visualization and analytics tools (Tableau, Looker, etc.)
• Background in NLP, information retrieval, or computational linguistics
• Experience on search or ML-focused teams
• Experience in eCommerce Search
• Knowledge of microservices architectures, event-driven systems, and CI/CD Pipelines

Qualifications

Must Haves

• Bachelor's degree in Computer Science, Engineering, Data Science, or a related quantitative field
• 3 years of hands-on experience in machine learning, data science, search relevance, or ranking systems
• Proven expertise in Python and ML frameworks (MLFlow, TensorFlow, PyTorch, Scikit-learn or equivalent)
• Strong background in statistical analysis, data exploration, and working with large-scale datasets
• Experience with feature engineering, data preprocessing, and data manipulation libraries (Pandas, NumPy, Spark)
• Demonstrated experience building or working with ranking models (learning-to-rank, neural ranking, or similar)
• Experience with semantic search, embedding, or dense retrieval methods
• Deep understanding of search engines (Elasticsearch, Solr, OpenSearch), lexical search algorithms (BM25), information retrieval concepts, search relevance tuning, tokenization, stemming, and query parsing
• Experience with MLOps practices and tools (model versioning, experiment tracking, pipeline orchestration)
• Proficiency in SQL and querying large datasets
• Strong problem-solving and analytical skills with the ability to think critically about complex search and ranking problems
• Excellent communication skills; ability to explain ML and search concepts to both technical and non-technical stakeholders
• Ability to collaborate with cross-functional teams

Nice to Haves

• Search Query Analysis: Analyze search query logs, evaluate user behavior data to identify opportunities for relevance improvements and inform ranking strategies
• Experience in training & fine tuning the models
• Experience with large language models (LLMs) or prompt engineering
• Experience with semantic indexing and dense vector search (e.g., vector databases)
• Experience in Search Metrics evolution
• Familiarity with data visualization and analytics tools (Tableau, Looker, etc.)
• Background in NLP, information retrieval, or computational linguistics
• Experience on search or ML-focused teams
• Experience in eCommerce Search
• Knowledge of microservices architectures, event-driven systems, and CI/CD Pipelines