Why Work at BNL?
Brookhaven National Laboratory (www.bnl.gov) delivers discovery science and transformative technology to power and secure the nation's future. Brookhaven Lab is a multidisciplinary laboratory with seven Nobel Prize-winning discoveries, 37 R&D 100 Awards, and more than 70 years of pioneering research. The Lab is primarily supported by the U.S. Department of Energy's (DOE) Office of Science. Brookhaven Science Associates (BSA) operates and manages the Laboratory for DOE. BSA is a partnership between Battelle and The Research Foundation for the State University of New York on behalf of Stony Brook University.

Organizational Overview

BNL's Electronic Detector Group (EDG) in the Physics Department at BNL has great strength in the study of the physics of flavor and an extensive history in kaon, muon and neutrino experiments and recent research in heavy flavor physics with the Belle II experiment. EDG physicists have major responsibilities in several neutrino experiments: the Deep Underground Neutrino Experiment (DUNE) and its prototype (ProtoDUNE), the short-baseline neutrino program (SBN includes MicroBooNE, SBND, and ICARUS), Daya Bay and PROSPECT. The EDG currently has twenty-five physicists at various career levels and a long history of research in fundamental particle physics. In collaboration with the Instrumentation Division, the group performs research and development in electronics and detector design for liquid-argon TPCs (LArTPC). In collaboration with the BNL Chemistry Department, the group performs research and development on water-based liquid scintillator and reactor neutrino experiments. In collaboration with the Computational Science Initiative (CSI), we develop new software and computing tools to advance intensity frontier research.

CSI is establishing BNL as a global leader in tackling the challenges of Big Data, Artificial Intelligence, Quantum Computing and High-Performance Computing, building on our existing expertise, capabilities, and investments in computational science and data management, and enabling scientific discovery in large-scale experimental environments. The mission of the CSI is to provide the laboratory an umbrella for research and development activities that address the computational needs of research programs both inside and outside of BNL, bringing together computer scientists, applied mathematicians and domain scientists to carry out leading edge research, convert research results into practical solutions that advance domain science and provide the necessary computing infrastructure services and training to support efficient operation.

Position Description

The Physics Department has an opening for a postdoctoral researcher to take a leading role in developing novel Machine Learning models to minimize systematic differences between simulations and real data. The position is in EDG and will be working closely with Machine Learning experts in CSI.

In addition, opportunities exist to participate in various related research topics carried out by EDG including involvement in current and designing future LArTPC experiments such as MicroBooNE, ProtoDUNE, ICARUS/SBND and DUNE. The selected candidate will have the opportunity to broaden impact by applying these techniques to additional experiments, such as the sPHENIX experiment at the Relativistic Heavy Ion Collider, a major new detector under construction at BNL. This position has a high level of interaction with the international and multicultural scientific community. A review of the applicants will start on January 4, 2021 and continue until the position is filled.

Essential Duties and Responsibilities:

• Lead role in developing and applying novel machine learning techniques
• Use advanced simulations and real detector output to prepare data sets for machine learning
• Validate results to improve simulations and the machine learning techniques

Position Requirements

Required Knowledge, Skills, and Abilities:

• PhD in high-energy particle or nuclear physics or related fields
• Familiarity with machine learning fundamentals, techniques and applications
• Strong programming ability and in particular, proficiency with modern C++ and Python
• Experience in HEP/NP offline software development
• Clear and concise written and interpersonal communication, and analytical skills

Preferred Knowledge, Skills, and Abilities:

• Understanding of Fourier analysis, convolutions, linear algebra
• Experience in HEP/NP physics analysis and working on collaborative software projects
• Use and development of particle detector event simulation and reconstruction software
• Experience with advanced machine learning techniques such as GANs
• Familiarity with ML software systems such as PyTorch, TensorFlow as well as Python's scientific software stack (numpy)
• Familiarity with software engineering practices that include testing, documentation, source code management, and release procedures
• Use of individual and clustered computing with Linux-based operating systems
• Experience with high-performance computing and heterogeneous computing (e.g. MPI, OpenMP, OpenACC and/or CUDA or message passing systems such as based on ZeroMQ)

Other Information:

• BNL policy requires that research associate appointments be made to individuals who have received their doctorate within the past five years.
• Initial two year term appointment subject to renewal contingent on performance and funding

At Brookhaven National Laboratory, we believe that a comprehensive employee benefits program is an important and meaningful part of the compensation employees receive. Our benefits program includes, but is not limited to:

• Medical, Dental, and Vision Care Plans
• Flexible Spending Accounts
• Paid Time-off and Leave Programs (vacation, holidays, sick leave, paid parental leave)
• 401(k) Plan
• Flexible Work Arrangements
• Tuition Assistance, Training and Professional Development Programs
• Employee Fitness/Wellness & Recreation: Gym/Basketball Courts, Weight Room, Fitness Classes, Indoor Pool, Tennis Courts, Sports Clubs/Activities (Basketball, Ping Pong, Softball, Tennis)