Back to jobs

AI Engineer

Pay
Pay not listed
Work setting
Not stated
Employment
Not stated

What you’ll work on

Full posting
  • Build hybrid retrieval and reranking over tens of millions of papers

  • Improve matching of papers and protocol steps to JoVE videos and timestamps

  • Build RAG and agentic pipelines that give cited answers with traceable claims

  • Build eval sets with scientific editors and gate releases on the results

  • Run models and LLM services in production, tracking latency and cost per query

From the employer’s posting
Build hybrid retrieval (BM25, sparse and dense embeddings) with reranking over tens of millions of papers.
Improve how papers and protocol steps are matched to JoVE videos and timestamps.
Build RAG and agentic pipelines for cited synthesis, Methods Q&A and troubleshooting. Every claim must trace to a source.
Build eval sets with scientific editors. Track relevance, citation accuracy, hallucination rate and match quality, and gate releases on them.
Ship and run models and LLM services in production. Watch latency and cost per query

What you’ll bring

All qualifications

Core experience

  • 4+ years in software or ML engineering, including 2+ years shipping LLM, search or NLP features to production.
  • Experience with scholarly data: PubMed, OpenAlex, Semantic Scholar, PMC, or entity extraction for genes, organisms and methods.
  • Strong Python and solid software engineering habits: testing, code review, CI/CD.
  • Experience with large-scale indexing (100M+ documents) and vector quantisation.
  • 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.
Qualification wording
4+ years in software or ML engineering, including 2+ years shipping LLM, search or NLP features to production.
Experience with scholarly data: PubMed, OpenAlex, Semantic Scholar, PMC, or entity extraction for genes, organisms and methods.
Strong Python and solid software engineering habits: testing, code review, CI/CD.
Experience with large-scale indexing (100M+ documents) and vector quantisation.
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.
Apply at JoVE

Posting record

Report an error

Actively hiringFirst seen by us 3 days ago, still listed, and not a repost of an earlier posting.

Status in our records
Live
First seen by us
Nov 18, 20263 days ago
Recorded sightings
4
Last seen by us
Nov 21, 2026
Employer says posted
Oct 29, 2026

These dates show when we found the posting. Check the employer’s website to confirm it is still accepting applications.

How this job compares

Time since we first saw it

Day 3

Similar jobs usually come down between day 1 and day 15.

From 1,368 similar postings that came down. Coming down is not always a hire.

JoVE is hiring

1 open job

Open jobs by the week we first saw them, last 12 weeks.

Hiring record

See how this role fits your experience

Add your resume and we’ll mark which of these tools you already use, and point out anything in the posting that could rule you out.

  • Python
  • AWS
  • Docker
  • Elasticsearch
  • Hugging Face
Where the posting names them
- 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 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.
- 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).
- 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.

Your next step

Complete your application on apply.workable.com. The employer’s form will show what is required.

Applying through Workable

  • No account needed. You can import your resume to fill in the form, or skip that and fill it in yourself.

Already applied? Track this application

Job description

View original posting ↗

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.

Requirements

  • 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.

Benefits

  • 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.

Demand for AI Engineer roles

New AI Engineer postings at the employers we follow are up 340% over the last 6 weeks compared with the 6 before.

Weekly new AI Engineer postings at the same employers, from the week of August 17 to the week of November 9. The fewest in a week was 78, the most 803, and the latest week had 438.
August 17Last week

Each bar is one week of new postings. The darkest bars are the last 6 weeks.

Counted from the hiring pages we’ve followed for at least five weeks, so employers we add don’t look like growth. Updated weekly.

About the role

We file this job under AI Engineer, by the work the posting describes.

AI engineers build products on top of AI models that already exist, most often large language models: they connect a model to a company's data and tools and ship the assistants, agents and search features people use.

Postings ask for strong Python or TypeScript, experience with model APIs, retrieval and agent frameworks, and ways to test whether the model's answers are good enough.

An ML engineer trains and serves models; an AI engineer usually starts from a model someone else trained and builds the product around it, though titles often mix the two.

Source details

View original posting ↗

Source notes

Source excerpts

Selected passages from the saved posting. Check the full description for conditions and exceptions.

Pay

No pay amount identified in the saved description.

Location & working pattern

India

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.
More source context
- 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.

More relevant text appears in the full description.

Work authorization

No clear work-authorization passage found. Eligibility is unconfirmed.

Find answers in the posting

AI
How answers work

AI selects complete passages from this posting. Check them for conditions and exceptions.

Uses this posting and your question. No profile needed.