AI Engineer

JoVE

United States

Remote

USD 130,000 - 190,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Benefits offered by this job

Fully remote
Competitive compensation

Job summary

JoVE seeks an AI Engineer to build the retrieval, matching and LLM systems behind our AI research products. You will own features end to end, from prototype to production, monitoring and cost, collaborating with product, JoVE editors, and data engineers.

You will deploy RAG pipelines, develop hybrid retrieval, and ensure citations trace to sources, while improving protocol understanding and video indexing across our paper-to-video platform.

Qualifications

  • 4+ years in software or ML engineering, including 2+ years shipping LLM, search or NLP features to production.
  • Strong Python and solid software engineering habits: testing, code review, CI/CD.
  • Hands-on experience building RAG systems: chunking, embeddings, hybrid retrieval, reranking and prompt design.
  • Experience with a vector or search engine such as Elasticsearch/OpenSearch, Milvus, pgvector, Qdrant or Pinecone.
  • Experience with LLM APIs (Anthropic, OpenAI or similar) and open models (Hugging Face, vLLM).
  • A track record of building offline evals and using metrics, not demos, to decide what ships.
  • Experience with agent frameworks, tool use, or building MCP servers.
  • Comfort with cloud infrastructure (AWS), Docker and API design.
  • Clear communication with non-engineers, including scientists and editors.

Responsibilities

  • Retrieval and search: Build hybrid retrieval (BM25, sparse and dense embeddings) with reranking over tens of millions of papers.
  • Paper-to-video matching: Improve how papers and protocol steps are matched to JoVE videos and timestamps.
  • AI answers with citations: Build RAG and agentic pipelines for cited synthesis, Methods Q&A and troubleshooting.
  • Protocol understanding: Extract method steps, reagents and parameters from papers and link to video chapters.
  • Evaluation: Build eval sets with scientific editors, track relevance and match quality, gate releases.
  • Production and cost: Ship and run models and LLM services in production, monitor latency and cost per query.
  • Platform and APIs: Help build APIs and an MCP server for AI assistants, ELNs and publisher widgets.
  • Instrumentation: Measure search, video click and watch funnel to improve ranking.

Skills

Python
Software engineering
Testing
CI/CD
Communication

Tools

Elasticsearch/OpenSearch
Milvus
pgvector
Qdrant
Pinecone
Hugging Face
vLLM

Job description

JoVE is the world-leading video platform for scientific research and education. Millions of scientists, educators and students worldwide use JoVE for their research, teaching and learning. Our institutional clients comprise over 1,000 universities, colleges, and biopharma companies, including leaders such as Harvard, MIT, and Stanford. As a rapidly growing company, with offices in the USA, UK, Australia, and India servicing clients in over 60 countries, we are seeking talented and ambitious individuals to join our company.

The Role

As an AI Engineer at JoVE, you will build the retrieval, matching and LLM systems behind our AI research products. You will own features end to end, from prototype and evaluation to production, monitoring and cost. You will work closely with product, the JoVE science editors, and the web and data engineers.

Responsibilities
  • Retrieval and search: Build hybrid retrieval (BM25, sparse and dense embeddings) with reranking over tens of millions of papers. Sources include PubMed, OpenAlex and PMC open-access full text.
  • Paper-to-video matching: Improve how papers and protocol steps are matched to JoVE videos and timestamps. Make matching aware of organism, technique and study type.
  • AI answers with citations: Build RAG and agentic pipelines for cited synthesis, Methods Q&A and troubleshooting. Every claim must trace to a source.
  • Protocol understanding: Extract method steps, reagents and parameters from papers. Link each step to the matching video chapter.
  • Evaluation: Build eval sets with scientific editors. Track relevance, citation accuracy, hallucination rate and match quality, and gate releases on them.
  • Production and cost: Ship and run models and LLM services in production. Watch latency and cost per query, and choose between hosted and open models.
  • Platform and APIs: Help build the APIs and an MCP server that let AI assistants, ELNs and publisher widgets use JoVE's methods data.
  • Instrumentation: Work with product to measure the search, video click and watch funnel, and use it to improve ranking.
  • 4+ years in software or ML engineering, including 2+ years shipping LLM, search or NLP features to production.
  • Strong Python and solid software engineering habits: testing, code review, CI/CD.
  • Hands-on experience building RAG systems: chunking, embeddings, hybrid retrieval, reranking and prompt design.
  • Experience with a vector or search engine such as Elasticsearch/OpenSearch, Milvus, pgvector, Qdrant or Pinecone.
  • Experience with LLM APIs (Anthropic, OpenAI or similar) and open models (Hugging Face, vLLM).
  • A track record of building offline evals and using metrics, not demos, to decide what ships.
  • Experience with agent frameworks, tool use, or building MCP servers.
  • Comfort with cloud infrastructure (AWS), Docker and API design.
  • Clear communication with non-engineers, including scientists and editors.
Nice to have
  • Experience with scholarly data: PubMed, OpenAlex, Semantic Scholar, PMC, or entity extraction for genes, organisms and methods.
  • Multimodal work: video transcripts, timestamp alignment, or image and video embeddings.
  • Fine-tuning embedding or reranker models, or learning-to-rank.
  • Experience with large-scale indexing (100M+ documents) and vector quantisation.
  • A competitive compensation package.
  • We are fully remote!
  • You will make a direct impact in accelerating science research and education.
  • Opportunity to work with global teams and in an environment that promotes innovation and collaboration.
  • Our strong promotion from within culture draws a clear path to advance your career with us.
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Remote AI Engineer – LLM, Retrieval & RAG Expert
Remote AI Engineer – LLM, Retrieval & RAG Expert

JoVE • United States

Remote
USD 130,000 - 190,000
Fully remote
Competitive compensation
AI Search & GEO Growth Specialist
AI Search & GEO Growth Specialist

JoVE • United States

On-site
USD 110,000 - 150,000
Product Manager (Life Sciences)
Product Manager (Life Sciences)

JoVE • United States

Remote
USD 120,000 - 180,000
Fully remote
Impact on science
Global teams
+2
Science Writer
Science Writer

JoVE • United States

Remote
USD 65,000 - 90,000
Unlimited manuscript acquisition bonus
Remote-friendly environment
Strong promotion from within
AI Engineer (Search & Matching) - fully remote within Germany (m/f/d) Remote
AI Engineer (Search & Matching) - fully remote within Germany (m/f/d) Remote

JobLeads GmbH • United States

Remote
USD 140,000 - 210,000
Senior AI Engineer: End-to-End AI Platforms Leader
Senior AI Engineer: End-to-End AI Platforms Leader

Jeeves Inc. • United States

Hybrid
USD 180,000 - 260,000
Assistant Review Manager, Journal
Assistant Review Manager, Journal

JoVE • United States

On-site
USD 90,000 - 150,000
AI Engineer
AI Engineer

Data • Union City (NJ)

On-site
USD 120,000 - 150,000
Creative Lead, Video Production
Creative Lead, Video Production

JoVE • United States

Remote
USD 120,000 - 180,000
Senior AI Engineer
Senior AI Engineer

Jeeves Inc. • United States

Hybrid
USD 180,000 - 260,000