Join us
Hello!
Are you a weirdo, passionate about science, a bit of a rockstar and above average geeky, driven by the idea of leaving a positive imprint of the world? Then come join us!
Below are our current openings. You are also welcome to send a general hello to
talent@iris.ai.
Job openings
Account Manager
Location: Sofia, Bulgaria
We are looking for a highly motivated Account Manager with a drive for providing exceptional customer service and knows their way around digital tools. You will be working mainly with large B2B client accounts coming from industries like Pharma, Chemical, BioTech, Material Science, Academia and other.
Learn more
Backend Python Developer
Location: Sofia, Bulgaria
IRIS.AI is an ML driven Science Assistant Machine that can read and understand scientific text. The Backend developer position is for bright and motivated people who enjoy dynamics and work with a product of global value.
Learn more
Research project 1
(Get in touch for research collaborations)
Enriching word embeddings with domain specific knowledge
RQ: What is the best way of introducing domain-specific knowledge into a general word embedding model, in order to produce high quality embeddings within that domain? How can we balance the information provided by the domain-specific corpus and the generic knowledge? After enriching the embeddings, how can we effectively measure the domain adaptation?
RQ: What is the best way of introducing domain-specific knowledge into a general word embedding model, in order to produce high quality embeddings within that domain? How can we balance the information provided by the domain-specific corpus and the generic knowledge? After enriching the embeddings, how can we effectively measure the domain adaptation?
Learn more
Research project 2
(Get in touch for research collaborations)
Enriching a knowledge base with domain-specific word embeddings
RQ: How do we best represent an existing knowledge base in a semantic space to relate its entities through contextual data? How do we best complete an annotated prototype knowledge base by injecting semantic relationships to defined entities based on their positions in the semantic space? By identifying their semantic properties through word embeddings, what is the best way to integrate these properties back into the knowledge base?
RQ: How do we best represent an existing knowledge base in a semantic space to relate its entities through contextual data? How do we best complete an annotated prototype knowledge base by injecting semantic relationships to defined entities based on their positions in the semantic space? By identifying their semantic properties through word embeddings, what is the best way to integrate these properties back into the knowledge base?
Learn more
Research project 3
(Get in touch for research collaborations)
Extending non-contextual word embeddings with word-sense disambiguation
RQ: What is the best way of extending a non-contextual word embeddings model, like Word2Vec, with word-sense disambiguation? How can we best represent different meanings of the same word in this enriched model? What is the best mechanism to determine the meaning of a word in a text, depending on its context? How can we best train such a word-sense disambiguation model?
RQ: What is the best way of extending a non-contextual word embeddings model, like Word2Vec, with word-sense disambiguation? How can we best represent different meanings of the same word in this enriched model? What is the best mechanism to determine the meaning of a word in a text, depending on its context? How can we best train such a word-sense disambiguation model?
Learn more
Research project 4
(Get in touch for research collaborations)
Generating tailored document summarization in response to specified topics of interest
RQ: How can we modify document summarization models to extract information relevant to specified topics? This could be to bias the summarization towards sections of relevance, such as results in a paper or patent, or to extract specific information from within a document, such as information relevant to a specific chemical within a general study.
RQ: How can we modify document summarization models to extract information relevant to specified topics? This could be to bias the summarization towards sections of relevance, such as results in a paper or patent, or to extract specific information from within a document, such as information relevant to a specific chemical within a general study.
Learn more
Research project 5
(Get in touch for research collaborations)
Improving extraction of tabular information from scientific text
RQ: How can we reliably and performantly detect tables in scientific publications from both machine-readable PDFs as well as from scanned images? How can we correctly detect their column- and row-boundaries to enable reliable extraction of the table content?
RQ: How can we reliably and performantly detect tables in scientific publications from both machine-readable PDFs as well as from scanned images? How can we correctly detect their column- and row-boundaries to enable reliable extraction of the table content?
Learn more
Research project 6
(Get in touch for research collaborations)
Scaling an embedding evaluation framework
RQ: How can we reliably measure the quality of a word embedding model trained for a new linguistic domain, in particular, for specific scientific domains? How can we get more detailed insights into the strengths and weaknesses of domain-specific embedding models? How can we use this information to iterate faster towards high-quality domain-specific embedding models?
RQ: How can we reliably measure the quality of a word embedding model trained for a new linguistic domain, in particular, for specific scientific domains? How can we get more detailed insights into the strengths and weaknesses of domain-specific embedding models? How can we use this information to iterate faster towards high-quality domain-specific embedding models?
Learn more




×
Get in touch!
Contact us to learn more!
Schedule a demo and learn more about how Iris.ai might work for your organization.
Opportunities at Iris.ai
Contact support!