• Design & Build: Architect and implement hybrid search methods combining vector databases with LLMs.
• Optimize & Scale: Lead the optimization of retrieval strategies and pipelines for high-recall compliance detection.
• Benchmark & Evaluate: Develop evaluation systems, drive continuous tuning, and set performance standards.
• Partner & Deliver: Collaborate with product and engineering to deliver new ML features end to end.

Requirements

Proven experience in ML or search engineering in production
Proficiency in Python and writing clean, maintainable code
Hands-on experience with LLMs, RAG architectures, and real-time inference systems
Experience designing, deploying, and maintaining ML systems in production
Experience working across back-end systems and search infrastructure
Experience building NLP evaluation systems
Bonus points if you have:
Experience with Vespa, OpenSearch, or similar search technologies
Data engineering or benchmarking system design
FastAPI framework experience
AWS cloud expertise
Startup or high-growth environment experience
Research background in ML or search
DevOps and CI/CD familiarity

🔍 ATS Optimization Keywords
Below are skills and terms extracted directly from this job posting to improve Applicant Tracking System (ATS) visibility. This unique feature helps candidates tailor their applications more effectively — a feature exclusive to JobTailor job listings.

Hard Skills

Python
LLMs
RAG architectures
real-time inference systems
NLP evaluation systems
data engineering
benchmarking system design
FastAPI
DevOps
CI/CD

Soft Skills

collaboration
leadership
optimization
evaluation
tuning

Senior AI Engineer

AI Leadership & Learning Specialist