Role: Senior AI/ML Engineer (Vector Store & Retrieval Systems) Location: Remote Duration:- Fulltime 10+ years in AI/ML or Data Engineering (healthcare domain preferred) to design, benchmark, and optimize text embedding and vector search solutions for large-scale clinical data. This role focuses on building high-performance pipelines and evaluating AI models to support intelligent search across patient records. Key Responsibilities:

• Develop and benchmark text chunking and embedding strategies
• Evaluate embedding models (OpenAI, Cohere, SBERT, etc.)
• Design and optimize vector search systems
• Build scalable pipelines for large datasets (up to billions of documents)
• Measure performance across cost, speed, scalability, and accuracy
• Support near real-time indexing and high query workloads
• Ensure compliance with PHI/HIPAA and enterprise security standards

Required Skills:

• Strong experience in AI/ML and NLP (embeddings, transformers)
• Hands-on with LLMs, RAG, and vector databases
• Proficiency in Python and data frameworks (Spark/Databricks)
• Experience with cloud platforms (Azure/AWS/GCP)
• Knowledge of distributed systems and high-throughput pipelines

Understanding of healthcare data and PHI compliance