Machine Learning Engineer, Search & Discovery

Posted 4 days ago

This is a fully remote position, open to applicants in United States.

📋 Description

• Develop and maintain advanced search and discovery features across Bask Health's applications.

• Create search services that extract relevant data from authorized platform data sources.

• Implement semantic search techniques utilizing embeddings and vector-based retrieval.

• Construct hybrid search systems that merge keyword matching with semantic retrieval.

• Design ranking and reranking methodologies to enhance the relevance of search results.

• Execute query processing, normalization, and comprehension functionalities.

• Establish search indexes and data pipelines to ensure that searchable information remains accurate and up to date.

• Develop APIs that provide search and retrieval capabilities to other applications.

• Integrate search functionalities into tools used by merchants and internal platforms.

• Facilitate information retrieval for AI assistants and retrieval-augmented generation systems.

• Implement filtering and metadata-driven retrieval for structured application data.

• Ensure that search functionalities adhere to user permissions and tenant boundaries.

• Create automated tests for assessing search behavior, retrieval quality, and ranking effectiveness.

• Generate evaluation datasets that reflect realistic search queries and anticipated outcomes.

• Measure search relevance using various retrieval and ranking metrics.

• Investigate search failures, absent results, and subpar rankings.

• Enhance search quality through experimentation and iterative adjustments to models or algorithms.

• Evaluate embedding models and retrieval settings for various applications.

• Implement monitoring for search latency, availability, and retrieval efficiency.

• Optimize search infrastructure for effective indexing and query execution.

• Collaborate with backend engineers to incorporate search services into the existing application framework.

• Work alongside product teams to pinpoint high-impact search and discovery opportunities.

• Create tools for debugging search results and comprehending ranking behaviors.

• Facilitate experiments related to search and controlled feature deployments.

• Enhance the reliability and maintainability of search pipelines and services.

• Participate in code reviews, technical planning, and architectural discussions.

• Document search configurations, evaluation methods, and implementation choices.

• Take ownership of assigned search and discovery projects from development to deployment and ongoing enhancement.


⛳️ Requirements

• Over 3 years of professional experience in machine learning engineering, software engineering, search engineering, or a related technical field.

• Proven experience in building and maintaining production software applications or data-driven systems.

• Proficient programming skills in Python, TypeScript, or similar languages.

• Understanding of the fundamentals of information retrieval and search systems.

• Experience in developing backend services and application APIs.

• Comprehension of search indexing, query processing, and ranking principles.

• Familiarity with machine learning techniques applied to search or information retrieval.

• Experience working with both structured and unstructured data sets.

• Knowledge of database queries and application data structures.

• Familiarity with embeddings and vector-based similarity search methodologies.

• Experience integrating search functionalities into software applications.

• Familiarity with evaluating search relevance and retrieval quality.

• Understanding of automated testing and practices in production software development.

• Proven track record of troubleshooting application performance and data quality issues.

• Familiarity with authentication, authorization, and secure data access protocols.

• Experience with cloud-based application deployment.

• Proficiency in using Git and collaborative software development practices.

• Ability to analyze search outcomes and identify relevance challenges.

• Familiarity with system performance, latency, and scalability factors.

• Experience writing maintainable and well-tested production code.

• Familiarity with logging, monitoring, and troubleshooting in production environments.

• Ability to translate product requirements into functional technical search capabilities.

• Strong analytical and problem-solving expertise.

• Capacity to collaborate effectively with product managers and engineers.

• Ability to independently manage assigned technical projects.

• Nice to Have: Experience in developing semantic search or hybrid search applications.

• Nice to Have: Familiarity with Elasticsearch, OpenSearch, or similar search technologies.

• Nice to Have: Experience with vector databases like Pinecone, Weaviate, Qdrant, or pgvector.

• Nice to Have: Experience implementing retrieval-augmented generation systems.

• Nice to Have: Familiarity with embedding models and vector similarity techniques.

• Nice to Have: Experience with learning-to-rank or neural reranking methodologies.

• Nice to Have: Understanding of BM25 and traditional information retrieval algorithms.

• Nice to Have: Familiarity with search evaluation metrics such as precision, recall, MRR, and NDCG.

• Nice to Have: Experience in creating search relevance evaluation datasets.

• Nice to Have: Experience with query rewriting, expansion, or intent classification.

• Nice to Have: Familiarity with large language models and AI-driven search applications.

• Nice to Have: Experience with OpenAI, Anthropic, or similar model APIs.

• Nice to Have: Experience building search features for SaaS or e-commerce platforms.

• Nice to Have: Familiarity with product catalogs, merchant data, or operational knowledge systems.

• Nice to Have: Experience with TypeScript and Node.js backend development.

• Nice to Have: Experience working with AWS or serverless infrastructures.

• Nice to Have: Familiarity with data pipelines and event-driven indexing.

• Nice to Have: Experience implementing permission-aware retrieval in multi-tenant applications.

• Nice to Have: Understanding of healthcare data privacy considerations.

• Nice to Have: Experience using AI-assisted development tools such as Cursor or Claude Code.


🏝️ Benefits

• Competitive salary and performance-based bonuses.

• Comprehensive health, dental, and vision insurance.

• Flexible work hours and remote work options.

• Professional development and training opportunities.

• A collaborative and inclusive work environment.

People also viewed

Memory Bridge10 hours ago

Senior Applied ML Engineer

US flagUnited States OnlyFull-timeMachine Learning Engineer
ApplyView job
Entrada11 hours ago

Senior Machine Learning Engineer, Databricks

PL flagPoland, +2 more countriesFull-timeMachine Learning Engineer
ApplyView job
Find Your Talent (FYT)13 hours ago

Senior Machine Learning Engineer

US flagUnited States OnlyFull-timeMachine Learning Engineer
ApplyView job
Inmetrics13 hours ago

Machine Learning Engineer

BR flagBrazil OnlyFull-timeMachine Learning Engineer
ApplyView job
SandboxAQ15 hours ago

Staff Machine Learning Engineer – Medical Devices

CA flagCanada OnlyFull-timeMachine Learning EngineerC$146k – C$258k/year
ApplyView job
StackAdapt15 hours ago

Staff Applied Machine Learning Scientist – Identity

US flagUnited States, +1 more countryFull-timeMachine Learning Engineer$182.4k – $250.8k/year
ApplyView job

Never miss a great job!

Get handpicked remote jobs straight to your inbox weekly.

Trusted by 7,400+ designers