Senior LLMOps & Semantic Search Engineer

Specialization: Gen AI & Machine Learning · Industries: E-Commerce & Retail, Customer Experience, Publishing · Vetting Rating: Interview-ready · LLM infrastructure review

Contract EngagementContractor / Deployable

AvailabilityAvailable in 1 week

Work ModelRemote worldwide

Benchmark Rate~$95 / hr

Verified Technical Stack:

Vector DatabasesCloudflare Workers AIEmbedding ModelsSemantic CachingPythonTypeScriptDockerKubernetesHugging Face TransformersTriton ServervLLM

Professional Summary

Production ML engineer focused on low-latency LLM inference, embedding pipelines, and semantic search at catalog scale.

Verified Impact & Project Highlights

Built semantic caching layer that materially reduced LLM token spend in production
Implemented automated prompt regression and evaluation suites using LLM-as-judge frameworks
Migrated legacy lexical search to hybrid dense-sparse retrieval with tracked quality and conversion readouts

Request an interview with HL-GENAI-814

Hiring teams only. We reply within one business day with slots. Candidate names stay off this site.

Engineer looking at this profile? Do not fill the interview form.Apply to join the bench.