NLP Engineer — Knowledge Search

Kwame Asante

Full-time · Mid-level · New_York

This role is no longer accepting applications

Similar open roles you can apply to now:

About the role

We sell enterprise search to firms with messy, private, high-value document collections. The problem sounds simple until you see the corpus: duplicate decks, inconsistent naming, old memos that still matter, and users who are allergic to irrelevant results. We need an NLP engineer to improve retrieval quality and trust. Better reranking, better query handling, better understanding of what a professional user is actually looking for. This is a focused product role with a lot of room for careful iteration.

Responsibilities

Improve semantic search and citation quality across large enterprise document corpora
Design reranking and query reformulation strategies for ambiguous professional-services queries
Build evaluation sets that reflect real user tasks rather than synthetic search benchmarks
Collaborate with product and customer success to understand where retrieval failure affects user trust most
Document index design, model choices, and tuning decisions so the team can iterate systematically

Requirements

3–5 years of NLP or search engineering experience in production systems
Python for retrieval services, evaluation, and experimentation
Hugging Face for embedding and reranking model workflows
LlamaIndex or LangChain for building document-centric retrieval systems
RAG experience focused on retrieval precision, citation quality, and corpus hygiene
SQL for metadata, usage analysis, and evaluation dataset management

Benefits

$96,000 – $116,000 base salary
Remote within the US or Canada
25 days PTO plus company holidays
$1,000 equipment refresh budget
Customers who know exactly when search is bad and are candid enough to help fix it