AI Engineer
JoVE (company site, opens in a new tab)4+ yrsRemoteDirect career pageEst. 18–30 LPA
Posted 17h ago
Reach people at JoVE
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at JoVE you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Develop and own end-to-end AI systems for retrieval, matching, and large language model (LLM) features powering AI research products.
- Build and optimize hybrid retrieval systems over tens of millions of scientific papers and improve paper-to-video matching with domain-aware enhancements.
- Manage production deployment, monitoring, cost optimization of models and LLM services, and collaborate on API/platform development enabling AI assistants and integrations.
Minimum Requirements
- Minimum 4 years in software or ML engineering, including at least 2 years shipping LLM, search, or NLP features to production.
- Strong Python programming skills and solid software engineering practices including testing, code review, and CI/CD.
- Hands-on experience building retrieval-augmented generation (RAG) systems with embeddings, hybrid retrieval methods, and prompt design.
- Experience with vector/search engines (e.g., Elasticsearch, Milvus, pgvector) and LLM APIs or open models, plus familiarity with cloud infrastructure (AWS), Docker, and API design.
Ideal Candidate Profile
- Experienced in building scalable, production-grade search and LLM-powered AI features for scientific or large-scale document domains.
- Comfortable working cross-functionally with product managers, scientific editors, and engineers, translating domain needs into technical solutions.
- Data-driven decision maker with proven history of building offline evaluation sets and gating releases based on rigorous metrics rather than demos.