You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
title: "Assistant Professor (Post-doc) – AI Interpretability",
6
+
subtitle:
7
+
"Centre for Credible AI, Warsaw University of Technology",
8
+
description:
9
+
"Research position focused on mechanistic interpretability and analysis of AI models, particularly attention mechanisms, within an interdisciplinary AI research environment.",
10
+
imageUrl: "/images/ccai.jpg",
11
+
imageAlt: "Centre for Credible AI at Warsaw University of Technology",
12
+
type: "Postdoc",
13
+
deadline: "2026-04-05",
14
+
location: "Warsaw, Poland",
15
+
salaryRange: "14 200–17 500 PLN gross/month",
16
+
employmentType: "Full-time",
17
+
workload: "40 hours per week",
18
+
contractType: "Employment contract",
19
+
referenceNumber: "FENG.02.01-IP.05-0058/24",
20
+
startDate: "2026-05-01",
21
+
organization:
22
+
"Centre for Credible Artificial Intelligence, Warsaw University of Technology",
23
+
detailedDescription:
24
+
"The Centre for Credible AI at Warsaw University of Technology is seeking a postdoctoral researcher to conduct advanced research in artificial intelligence, with a focus on interpretability and analysis of modern AI systems. The position is funded under the FENG MAB project and offers an opportunity to work in a highly interdisciplinary environment combining machine learning, mathematics, and applied sciences. The successful candidate will contribute to research on understanding internal mechanisms of AI models, particularly attention-based architectures, and collaborate with a team of researchers while mentoring junior members.",
25
+
requirements: [
26
+
"PhD in computer science, artificial intelligence, mathematics, physics, or a related field (obtained within the last 5 years)",
27
+
"Proven experience in AI model interpretability or analysis, especially attention mechanisms",
28
+
"Ability to conduct independent research",
29
+
"Strong teamwork and interdisciplinary collaboration skills",
30
+
"Very good command of English",
31
+
],
32
+
responsibilities: [
33
+
"Conduct independent and collaborative research in AI interpretability",
34
+
"Develop methods for analyzing internal mechanisms of AI models",
35
+
"Work on attention-based and modern ML architectures",
36
+
"Collaborate within interdisciplinary research teams",
37
+
"Support and mentor junior researchers",
38
+
],
39
+
benefits: [
40
+
"Competitive salary funded by a national research program",
41
+
"Work in a leading AI research center (CCAI)",
42
+
"Access to interdisciplinary collaborations",
43
+
"Participation in international research projects",
0 commit comments