Saurabh Jha is a staff research scientist at IBM Research in Yorktown Heights, NY, a position he has held since 2021. In 2024, he was appointed as the Research Product Focal (PI) for Instana, facilitating strategic collaboration between IBM Research and IBM Instana. He earned his Ph.D. in 2021 and his M.S. in Computer Science in 2016 from the University of Illinois at Urbana-Champaign (UIUC), following his B.Tech from VIT University. Before joining UIUC, he was a visiting scholar at NTU Singapore and he has previously worked with IBM, NVIDIA Research, and Microsoft Research as an intern or consultant.
Saurabh’s expertise lies at the intersection of Machine Learning and Systems. His research has contributed to the integration of several innovative features into products deployed at scale. Most notably, his work has significantly enhanced the analytics capabilities of IBM Instana and Turbonomic, improving the resilience and performance of IT applications. Additionally, his work contributed to the improved resilience of Nvidia’s DriveAGX platform for self-driving cars. He is currently focused on developing orchestration frameworks for multi-modal AI inference systems and multi-agent systems to create breakthrough applications such as SREagent.
Saurabh has received numerous accolades, including the IBM Tech Award in 2024, the IBM Ph.D. Fellowship (2020-2021), the SAP Industry Ph.D. Scholarship (2014), and the VIT University Best Outgoing Student Award (2014). His work has earned best paper awards and honorable mentions at prestigious conferences such as ACM/IEEE SC 2020, IEEE ISSRE 2020, and ACM HPDC 2013.
Visit one of the following:
Publications,
Google Scholar,
DBLP
- (2024/04/18) Our work on probable root cause identification was integrated into Instana as an innovative feature, now available in tech preview for select customers. Announcement Interview
- (2024/05/01) "Power-aware Deep Learning Model Serving with μ-Serve" accepted at ATC 2024. Paper link
- (2024/04/31) "iPrism: Characterize and Mitigate Risk by Quantifying Change in Escape Routes" accepted at DSN 2024. This work is based on my PhD dissertation.
- (2024/02/23) Our work on GenAI observability was integrated as an innovative feature in Instana, now available in tech preview for select customers. Announcement
- (2024/01/25) Selected to participate IBM Tech 2024; <0.01% of IBMers are selected. IBM Tech 2024 is IBM's premier recognition, education, and development program for top technical IBMers who have made vital contributions to some of IBM's most innovative and impactful technologies.
- (2024/01/03) Appointed as Research Product Focal (PI) for IBM Instana, I will collaborate with both IBM Research and the Instana teams to reimagine and innovate the observability platform, in addition to my existing responsibilities. Read about IBM Instana here.
- Organizing committee : DSN 2024 Industry Track Chair, ISSRE 2023 Industry Track Chair, Co-chair DSN-DSML 2022
- 2024 : NeurIPS, DSN
- 2023 : IPDPS,
ICRA, DSN, DISRUPT
- 2022 :
SoCC,
Cluster,
ICML,
IROS,
ICLR,
RA-L,
NeurIPS,
OLTS,
ISSRE
- 2021 :
ICML,
IROS,
NeurIPS,
HPCMASPA,
RA-L
- 2020 :
EuroSys (Shadow PC),
TOC,
TON
- 2019 :
SOSP (artifact)
- 2018 :
TDSC
- 2017 :
TPDS,
HPCMASPA,
SC (external)