NLP (Natural Language Processing) Apps Developer Inside IR35
Recruiter
Listed on
Location
Salary/Rate
Salary Notes
Type
Start Date
This job has now expired please search on the home page to find live IT Jobs.
My client is looking for a NLP (Text Analyst) to create a graph database of a text network, to work on an initial 6 month contract fully remote from home.
Overall Purpose:
To develop and embed NLP applications in the domain of Health and Safety. This role will support the ongoing development of a team and applications to analyse text data associated with health and safety incidents and investigations.
The client is looking to create a graph database of a text network. They will start with SQL and ingest the data into a no-sql graph database.
Key language is Python.
Ontology experience is a nice to have.
Text mining field, will need to have some experience and be a competent coder in Python to create models, do cluster analysis. They will be text mining alongside a graph[h network.
Focus is NLP, Text analysis and Python.
Key Responsibilities:
* Designing and developing and refining existing NLP applications
* Using effective text representation techniques and classification algorithms
* Training and evaluating models
* Supporting an overall strategy to converge on text mining tools and approaches within my client.
Essential Skills and Experience:
Python:
* use of the following text analysis libraries: spaCy, nltk, transformers, AllenNLP
* use of the machine learning library Scikit-Learn library and deep-learning libraries such as pytorch, and tensorflow/keras
* interfacing with SQL databases
Other essential coding skills:
* Use of version control systems
* Writing unit tests
* Code documentation
Other desirable coding skills:
* Text extraction from a range of document formats
* Experience with non-relational databases
* API development & documentation
* Web-development using e.g. node.js or flask
* Web scraping using e.g. Beautiful Soup and Scrapy
NLP/TM experience:
* Using and fine tuning/training transformer models such as BERT for a variety of NLP tasks, including entity classification, document classification, document summarization, question answering
* Developing systems for information retrieval, using methods for relevance ranking
* Generating and using annotated data for training NLP models
* Application of a variety of machine learning algorithms for tasks such as document clustering
* Using OpenIE libraries for entity and relation extraction (e.g. for use in a knowledge graph)
* Normalisation of entities and coreference resolution
* Using appropriate NLP performance metrics to assess and improve algorithm performance
Daily rate £500pd Inside IR35
REMOTE FROM HOME