About the Role
We're looking for a Senior Machine Learning Engineer, Search & Personalization to design, build, and improve intelligent search, discovery, and personalization capabilities across Bask Health's platform.
This is a hands-on engineering role focused on making information easier to find, experiences more relevant, and complex workflows more intuitive. You'll work with machine learning models, information retrieval systems, embeddings, ranking algorithms, and production application infrastructure to build search and recommendation experiences that deliver measurable value.
Bask Health supports multiple interconnected applications, including merchant-facing tools, patient experiences, clinical workflows, pharmacy operations, and commerce systems. You'll help develop the underlying intelligence that allows these applications to surface useful information, prioritize relevant results, and adapt experiences to different user needs.
Your work may include semantic search, hybrid retrieval, intelligent ranking, contextual recommendations, personalized content discovery, and retrieval services that support AI-powered applications.
You'll be responsible for more than model experimentation. You'll design and deploy production systems, develop data pipelines, establish evaluation methods, monitor performance, and improve search relevance through ongoing testing and iteration.
You'll collaborate closely with product managers, backend engineers, frontend engineers, and applied AI teams to understand how users interact with the platform and where better discovery or personalization can reduce friction.
Because Bask operates in healthcare-related environments, you'll also need to consider privacy, access controls, and the limitations of personalized recommendations. Systems that influence sensitive healthcare workflows must follow approved product and clinical boundaries rather than independently making medical decisions.
We're looking for someone who combines strong machine learning fundamentals with practical software engineering skills and enjoys building intelligent systems that people use every day.
What You'll Do- Design, build, and deploy machine learning systems for search, discovery, ranking, and personalization.
- Develop semantic search capabilities that improve how users find information across Bask Health's applications.
- Build and optimize retrieval pipelines using embeddings, vector search, and traditional search methods.
- Design hybrid search systems combining lexical matching, semantic retrieval, and relevance ranking.
- Develop ranking models and algorithms that prioritize useful search results.
- Build recommendation systems that surface relevant platform features, resources, or workflow information.
- Develop contextual personalization capabilities based on approved user and application signals.
- Work with product teams to identify opportunities to improve search relevance and information discovery.
- Build scalable indexing, retrieval, and search-serving infrastructure.
- Design data pipelines that support search models, ranking systems, and recommendation features.
- Develop approaches for generating, storing, updating, and evaluating embeddings.
- Experiment with learning-to-rank methods and machine learning-based relevance improvements.
- Implement query understanding, query expansion, and search intent interpretation where appropriate.
- Improve search performance across structured and unstructured data sources.
- Collaborate with applied AI engineers to support retrieval-augmented generation applications.
- Develop retrieval services that can be reused across patient, merchant, and operational applications.
- Define and track search quality metrics, including relevance, recall, precision, and ranking performance.
- Design offline evaluation datasets and benchmarking procedures for search and recommendation systems.
- Collaborate with product teams to conduct controlled experiments and measure user experience improvements.
- Optimize search latency, throughput, infrastructure utilization, and operational costs.
- Implement monitoring and observability for production search and personalization services.
- Investigate search quality issues, indexing failures, and ranking inconsistencies.
- Ensure retrieval and personalization systems respect user permissions and data access boundaries.
- Design appropriate safeguards for sensitive healthcare-related recommendations.
- Work with backend and frontend engineers to integrate search and recommendation features into production applications.
- Contribute to architecture decisions involving search infrastructure, databases, and machine learning services.
- Mentor engineers and share expertise in information retrieval, ranking, and production ML engineering.
- Own search and personalization initiatives from technical design through deployment, measurement, and ongoing improvement.
Requirements- 5+ years of professional experience in machine learning engineering, software engineering, search engineering, or a closely related technical discipline.
- Demonstrated experience building and deploying machine learning systems in production.
- Strong programming skills in Python and experience developing production software services.
- Experience building search, recommendation, ranking, or information retrieval systems.
- Strong understanding of machine learning fundamentals and applied statistical methods.
- Familiarity with modern information retrieval techniques and search relevance optimization.
- Experience with embeddings, vector representations, or semantic similarity methods.
- Understanding of lexical search, semantic search, and hybrid retrieval approaches.
- Experience designing or integrating scalable search infrastructure.
- Strong understanding of ranking algorithms and relevance evaluation.
- Experience working with structured and unstructured datasets.
- Familiarity with data processing, feature engineering, and machine learning pipelines.
- Experience building backend APIs and integrating machine learning services into applications.
- Understanding of database design, indexing, and query performance.
- Experience evaluating model or search system performance using quantitative metrics.
- Familiarity with offline evaluation, experimentation, and performance benchmarking.
- Experience optimizing production systems for latency, scalability, and reliability.
- Understanding of cloud infrastructure and deployment practices.
- Familiarity with monitoring, logging, and troubleshooting production services.
- Strong software engineering practices, including testing, code review, and version control.
- Understanding of data privacy, access controls, and secure application design.
- Ability to translate product requirements into practical machine learning solutions.
- Experience collaborating with product managers and cross-functional engineering teams.
- Ability to independently own complex engineering projects from design through deployment.
- Strong analytical thinking, communication skills, and technical problem-solving abilities.
Nice to Have- Experience building personalized recommendation systems for SaaS or consumer applications.
- Familiarity with learning-to-rank models and neural ranking approaches.
- Experience with approximate nearest neighbor search and vector indexing techniques.
- Familiarity with Elasticsearch, OpenSearch, Vespa, or comparable search infrastructure.
- Experience using vector databases such as Pinecone, Weaviate, Milvus, or pgvector.
- Experience with embedding models and transformer-based retrieval systems.
- Familiarity with cross-encoders, reranking models, and multi-stage retrieval pipelines.
- Experience developing query understanding or natural language search features.
- Experience building retrieval systems for large language model applications.
- Familiarity with retrieval-augmented generation architectures.
- Experience with recommendation approaches such as collaborative filtering or content-based ranking.
- Experience with online experimentation, A/B testing, and search relevance measurement.
- Familiarity with clickstream analysis and user behavior modeling.
- Experience developing real-time or near-real-time personalization systems.
- Experience with large-scale data processing frameworks or distributed computing.
- Familiarity with AWS and cloud-based machine learning infrastructure.
- Experience building search or recommendation features for e-commerce platforms.
- Experience with healthcare, telehealth, or other privacy-sensitive software.
- Understanding of HIPAA and healthcare data privacy considerations.
- Experience using AI-assisted development tools such as Cursor or Claude Code.
