Research Fellow in NLP for Sign Language Translation
| Dyddiad hysbysebu: | 11 Chwefror 2026 |
|---|---|
| Cyflog: | £36,636 i £41,064 bob blwyddyn |
| Oriau: | Llawn Amser |
| Dyddiad cau: | 11 Mawrth 2026 |
| Lleoliad: | Southampton, Hampshire |
| Gweithio o bell: | Ar y safle yn unig |
| Cwmni: | University of Southampton |
| Math o swydd: | Cytundeb |
| Cyfeirnod swydd: | 3337026FP |
Crynodeb
Join the project shaping the future of inclusive technology
At the University of Southampton, our research addresses some of the most pressing challenges of today’s world. Now, funded by EPSRC, we are looking for a talented Postdoctoral Research Fellow to join the RADAR-SIGN-BRIDGE project – an exciting initiative to develop privacy-preserving radar technology for British Sign Language (BSL) recognition and translation.
You will be based in the School of Electronics and Computer Science (ECS), working alongside an interdisciplinary team led by Dr. Shelly Vishwakarma (s.vishwakarma@soton.ac.uk), in collaboration with partners at the University of Edinburgh (Centre for Speech Technology Research, CSTR) and University College London (Deafness Cognition and Language Research Centre, DCAL).
About the role
You will lead the natural language processing and language modelling aspects of the project, focusing on how sensor-derived motion data (from radar) can be transformed into linguistically meaningful BSL representations and translated into written language. Your work will sit at the interface between sensor data, sign language structure, and NLP, enabling end-to-end sign language translation that goes beyond simple gesture recognition.
As part of the team, you will:
Develop NLP models that map sensor-level representations to BSL-aware language units.
Work with radar and annotated sign language datasets.
Explore modern sequence modelling approaches (e.g. transformers).
Collaborate with linguists and Deaf researchers to ensure linguistic validity.
Write academic papers, contribute to open-source dataset releases, and present your work at international conferences
About you
A PhD* or equivalent qualification/experience in Computer Science, NLP, AI, or a related field.
Strong experience in natural language processing or machine learning.
Excellent programming skills in Python and deep learning frameworks.
A collaborative mindset and interest in socially impactful research.
Experience with sign language data, multimodal learning, or radar sensing is advantageous but not essential. Any prior knowledge of radar or sensing technologies will be considered a bonus.
What we can offer you?
The University of Southampton is a top university (1% globally), and ECS is one of the top-ranked schools for Electronic Engineering and Computer Science in the UK. You'll also benefit from ECS’s links to the ARM-ECS Research Centre, the MINDS CDT, and the Future Worlds startup accelerator.
As a founding signatory of the Athena SWAN charter, and holder of a silver award, we’re committed to improving equality. We aim to create an environment where everyone can thrive and are proactive in fostering a culture of inclusion, respect and equality of opportunity. As well as additional benefits that will make your life easier, such as a generous holiday allowance and additional university closure days, we will help you find a good work-life balance with flexible working hours. We will support your long-term future too, with access to the Universities Superannuation Scheme (USS)*, subsidised health and fitness facilities and a range of discounts.
Learn more about ECS at: https://talentedu.com/ecs/
We strongly encourage interested candidates to contact Dr. Shelly Vishwakarma (s.vishwakarma@soton.ac.uk) to discuss this role further.
We are committed to equality, diversity and inclusion and welcome applicants who support our mission of inclusivity.
Apply by 11.59 pm GMT on the closing date. For assistance contact Recruitment on +44(0)2380 592750 or recruitment@soton.ac.uk quoting the job number.
At the University of Southampton, our research addresses some of the most pressing challenges of today’s world. Now, funded by EPSRC, we are looking for a talented Postdoctoral Research Fellow to join the RADAR-SIGN-BRIDGE project – an exciting initiative to develop privacy-preserving radar technology for British Sign Language (BSL) recognition and translation.
You will be based in the School of Electronics and Computer Science (ECS), working alongside an interdisciplinary team led by Dr. Shelly Vishwakarma (s.vishwakarma@soton.ac.uk), in collaboration with partners at the University of Edinburgh (Centre for Speech Technology Research, CSTR) and University College London (Deafness Cognition and Language Research Centre, DCAL).
About the role
You will lead the natural language processing and language modelling aspects of the project, focusing on how sensor-derived motion data (from radar) can be transformed into linguistically meaningful BSL representations and translated into written language. Your work will sit at the interface between sensor data, sign language structure, and NLP, enabling end-to-end sign language translation that goes beyond simple gesture recognition.
As part of the team, you will:
Develop NLP models that map sensor-level representations to BSL-aware language units.
Work with radar and annotated sign language datasets.
Explore modern sequence modelling approaches (e.g. transformers).
Collaborate with linguists and Deaf researchers to ensure linguistic validity.
Write academic papers, contribute to open-source dataset releases, and present your work at international conferences
About you
A PhD* or equivalent qualification/experience in Computer Science, NLP, AI, or a related field.
Strong experience in natural language processing or machine learning.
Excellent programming skills in Python and deep learning frameworks.
A collaborative mindset and interest in socially impactful research.
Experience with sign language data, multimodal learning, or radar sensing is advantageous but not essential. Any prior knowledge of radar or sensing technologies will be considered a bonus.
What we can offer you?
The University of Southampton is a top university (1% globally), and ECS is one of the top-ranked schools for Electronic Engineering and Computer Science in the UK. You'll also benefit from ECS’s links to the ARM-ECS Research Centre, the MINDS CDT, and the Future Worlds startup accelerator.
As a founding signatory of the Athena SWAN charter, and holder of a silver award, we’re committed to improving equality. We aim to create an environment where everyone can thrive and are proactive in fostering a culture of inclusion, respect and equality of opportunity. As well as additional benefits that will make your life easier, such as a generous holiday allowance and additional university closure days, we will help you find a good work-life balance with flexible working hours. We will support your long-term future too, with access to the Universities Superannuation Scheme (USS)*, subsidised health and fitness facilities and a range of discounts.
Learn more about ECS at: https://talentedu.com/ecs/
We strongly encourage interested candidates to contact Dr. Shelly Vishwakarma (s.vishwakarma@soton.ac.uk) to discuss this role further.
We are committed to equality, diversity and inclusion and welcome applicants who support our mission of inclusivity.
Apply by 11.59 pm GMT on the closing date. For assistance contact Recruitment on +44(0)2380 592750 or recruitment@soton.ac.uk quoting the job number.
Aelod balch o'r cynllun cyflogwyr Hyderus o ran Anabledd
Hyderus o ran Anabledd
Gwybodaeth am Hyderus o ran Anabledd
Yn gyffredinol, bydd cyflogwr Hyderus o ran Anabledd yn cynnig cyfweliad i unrhyw ymgeisydd sy'n datgan eu bod yn anabl ac yn bodloni'r meini prawf lleiaf ar gyfer y swydd fel y diffinnir gan y cyflogwr. Mae'n bwysig nodi, mewn rhai sefyllfaoedd recriwtio fel nifer fawr o ymgeiswyr, cyfnod tymhorol ac amseroedd prysur iawn, efallai y bydd y cyflogwr am gyfyngu ar y niferoedd cyffredinol o gyfweliadau a gynigir i bobl anabl a phobl nad ydynt yn anabl. Am fwy o fanylion ewch i Hyderus o ran Anabledd.