Machine Learning Engineer - Search and Indexing

About TableCheck

TableCheck is seeking a talented Machine Learning Engineer specializing in Search and Indexing to join our growing AI team. This role is critical in building and optimizing the search infrastructure that powers our platform's core capabilities.

Role Overview

We're looking for an experienced ML engineer who can bridge the gap between traditional search technologies and modern AI-powered solutions. You'll be responsible for designing, implementing, and optimizing search systems that combine the best of both worlds - leveraging classical information retrieval techniques alongside cutting-edge vector search and neural approaches.

Key Responsibilities

Search Infrastructure Development

• Design and implement scalable search systems combining traditional keyword-based and semantic vector search capabilities
• Build and optimize hybrid search architectures that intelligently blend lexical and semantic matching
• Develop and maintain vector database solutions for efficient similarity search at scale
• Create robust indexing pipelines that handle real-time data ingestion and updates

Model Development and Optimization

• Fine-tune pre-trained language models for domain-specific search and retrieval tasks
• Implement and optimize re-ranking models to improve search result relevance
• Build classification models for query understanding, intent detection, and result categorization
• Develop custom embedding models tailored to our specific use cases

Search Quality and Performance

• Design and implement A/B testing frameworks for search improvements
• Establish metrics and evaluation frameworks for search quality assessment
• Optimize query latency and throughput while maintaining result quality
• Implement caching strategies and performance optimizations for production systems

Collaboration and Innovation

• Work closely with product teams to understand search requirements and user needs
• Collaborate with data scientists to integrate ML models into search pipelines
• Partner with engineering teams to ensure smooth deployment and scaling
• Stay current with latest developments in search technology and machine learning

Required Qualifications

Technical Expertise

• 3+ years of experience building production search systems
• Strong understanding of traditional search technologies (Elasticsearch, Solr, Lucene)
• Hands-on experience with vector databases (Pinecone, Weaviate, Milvus, Qdrant, or similar)
• Proven experience implementing hybrid search systems combining keyword and semantic search
• Expertise in fine-tuning transformer models (BERT, RoBERTa, Sentence Transformers, etc.)
• Strong background in traditional ML techniques for ranking and classification (XGBoost, LightGBM, learning-to-rank)
• Experience with MLOps practices and model deployment pipelines

Educational Background

• 3 years of experience or a bachelor's degree in Computer Science, Machine Learning, or related field.

Nice-to-Have Qualifications

• Experience with multi-modal search (text, image, structured data)
• Familiarity with query understanding and expansion techniques
• Experience with personalized search and recommendation systems
• Contributions to open-source search or ML projects will be highly considered

What We Offer

• Remote work
• Opportunity to work on challenging search problems at scale
• Collaborative environment working directly with a full-stack team, talented engineers and data scientists

How to Apply

If you're passionate about building intelligent search systems that combine the best of traditional and modern approaches, we'd love to hear from you. Please submit your resume containing a clear description of your most impactful search or ML project.

NOTE: This is a contract-only role and is not eligible for relocation.