
INNOVATION PLACEMENT IN RADIO ASTRONOMY
In collaboration with ATOS and the University of Manchester, DiRAC is pleased to invite applications for a 6-month Innovation Placement focussing on a Quantum Machine Learning pulsar classification model in the field of Radio Astronomy.
Applications are now closed
DiRAC Innovation Placements are a great opportunity for students and early career researchers to work with deep technology companies on 6-month industry-academia projects, using cutting-edge approaches to learn new skills. The project is designed to address a particular research challenge and provide useful insight to both the academic University partner and the industrial partner.
You must get your supervisor’s or PI’s permission before applying for this placement. Participation in the placement scheme is allowed under UKRI’s rules, but only with your supervisor/PI’s consent. We will do our best to be flexible; part time working can be arranged as long as the placement does not exceed 9 months.
Background:

The Atos Quantum Learning Machine (Atos QLM) is a complete environment designed for quantum software developers. It is dedicated to the development of quantum software, training and experimentation and embeds a programming platform and a high-performance quantum simulator. The QLM allows researchers to develop and experiment with quantum software and emulates execution as a genuine quantum computer would. myQLM is a bespoke python package designed to democratize quantum computing by allowing researchers and developers to create and simulate quantum circuits on their laptops. It is fully compatible with the Atos QLM and the successful applicant will launch their myQLM program on Atos QLM to benefit from larger simulation capabilities and advanced features like quantum circuit optimizers and noisy simulators. For more information on the Atos QLM and myQLM see: https://atos.net/en/solutions/quantum-learning-machine.
Project Description:
This project will work with the Quantum Machine Learning (QML) pulsar classification model from Kordzanganeh, Utting & Scaife (NeurIPS 2021) and will be divided into 2 phases, each lasting approximately 3 months.
Phase 1: The initial learning phase will be devoted to understanding the basics of Quantum Computing and myQLM using training materials provided by Atos. The successful candidate will also gain a familiarisation of the details of Kordzanganeh, Utting & Scaife (NeurIPS 2021) and compare and contextualise that model with respect to the Atos materials. Deliverables from this initial phase will be training material including an introduction to ‘Quantum Computing for Radio Astronomy’.
Phase 2: The QLM model will be used to investigate the performance of the QAUM data-encoding introduced in that paper, compared to more standard encodings such as QAOA (Quantum Approximate Optimization Algorithm), when deployed on simulated quantum computing systems of varying coherence times. If time permits, this work will also incorporate:
(i) evaluation of empirical machine learning model capacity measures for different encoding depths, and/or
(ii) a trade-off analysis exploring the computational cost of using different numbers of qubits vs. different levels of parallelisation as a function of machine learning model performance.
The deliverable from this phase will be a myQLM / QLM implementation of the QML pulsar classification model from Kordzanganeh, Utting & Scaife (NeurIPS 2021)
Prerequisite:
This project is suitable for students who have experience in Python programming. Experience with deep-learning is desirable but not required, as the principles of QML will be covered in the first 3 months of the internship. No previous experience of quantum computing is required. Code for the QML pulsar classification model is available in Python (using the pennylane QML library).
Placement:
In Phase 1 the successful candidate will work with Atos training staff and collaborators of Professor Anna Scaife (University of Manchester Astronomy and Astrophysics Theory Group) as a research point of contact. Phase 2 will be mentored by Professor Anna Scaife. It is expected that the placement will be fully remote.
Application Process:
- The Closing date for applications is 12pm Monday 21st March 2022
- Ideally, the candidate would start on or before 31st March 2022, but later start dates can be accommodated if necessary.
- Speak to your current supervisor/line manager and get their views BEFORE applying.
- Contact Clare Jenner, DiRAC Deputy Director & Project Scientist, c.jenner@ucl.ac.uk, if you need further information.
- Complete the application form here.
- Send your completed application form and CV to Clare Jenner c.jenner@ucl.ac.uk
- Selection process: shortlisted candidates will be invited to attend a zoom interview with representatives from both DiRAC and the placement hosts.