LL
Full time
🤖 AI / ML
AI Research Scientist at Lexsi Labs
Listed by DevShelfHub
Bangalore, India (Hybrid)
Hybrid
Mid-level · 2–5 yrs
About the Role
As AI capabilities scale toward advanced autonomous intelligence, the need for safe, interpretable, and aligned AI systems has never been more critical. Lexsi Labs, a frontier AI research lab with hubs in Mumbai and Paris, is hiring an AI Research Scientist in Bangalore to work on fundamental research in agent learning, alignment, and interpretability.
This hybrid, full-time role offers the opportunity to pursue ambitious research while contributing to open science and global collaboration.
What you'll do
- The AI Research Scientist will work on fundamental research problems at the frontier of agent learning, reinforcement learning, interpretability, and alignment.
- Conduct foundational research on multi-agent reinforcement learning, agent exploration, continual learning, and scalable alignment strategies
- Design and evaluate algorithms that improve the learning efficiency, coordination, and controllability of large AI systems
- Develop methods for interpreting and analyzing internal model behavior, including representation analysis, circuit discovery, and causal reasoning tools
- Investigate alignment techniques such as reward modeling, safety fine-tuning, pruning, unlearning, and training-time behavioral control
- Explore information-theoretic and causal approaches for understanding how models represent knowledge and make decisions
- Build research infrastructure and experimental frameworks for RL training, alignment experiments, and large-scale evaluation
- Publish research in leading venues and contribute to open-source tools and alignment research infrastructure
What we're looking for
- PhD or Masters or equivalent research experience in Machine Learning, Artificial Intelligence, Computer Science, Mathematics, Physics, or related fields
- Strong background in reinforcement learning, multi-agent systems, large language models, interpretability, deep learning theory, or information-theoretic ML
- Proven ability to conduct independent research and publish in top-tier AI conferences such as NeurIPS, ICML, ICLR, ACL, CVPR, or AAAI
- Hands-on experience training and experimenting with models using frameworks such as PyTorch, JAX, or TensorFlow
Skills & Technologies
Required
PhD or Masters or equivalent research experience in Machine Learning, Artificial Intelligence, Computer Science, Mathematics, Physics, or related fields
Strong background in reinforcement learning, multi-agent systems, large language models, interpretability, deep learning theory, or information-theoretic ML
Proven ability to conduct independent research and publish in top-tier AI conferences such as NeurIPS, ICML, ICLR, ACL, CVPR, or AAAI
Hands-on experience training and experimenting with models using frameworks such as PyTorch, JAX, or TensorFlow
Strong programming and experimentation skills in Python and modern ML research tooling
Demonstrated interest in AI alignment, safety, interpretability, or trustworthy AI systems
Benefits & Perks
- Health Insurance
- Flexible Leave Policy
- Learning Budget
- EPF / NPS
Why This Role is Good for Experienced Professionals
- This role is ideal for researchers passionate about AI safety, alignment, and interpretability at the frontier of the field.
- Conduct foundational research on multi-agent reinforcement learning and scalable alignment strategies
- Design algorithms that improve learning efficiency, coordination, and controllability of large AI systems
- Develop methods for interpreting and analyzing internal model behavior
- Investigate alignment techniques including reward modeling, safety fine-tuning, pruning, and unlearning
- Explore information-theoretic and causal approaches for understanding model decision-making
- Build research infrastructure for RL training, alignment experiments, and large-scale evaluation
- Publish research in leading venues and contribute to open-source tools
- Collaborate with a team building next-generation alignment methods and agent learning systems
- Work in a research-oriented environment with global hubs in Mumbai and Paris
- Pursue ambitious research ideas with open science and global collaboration
About Lexsi Labs
Lexsi Labs is a frontier AI research lab focused on building safe, interpretable, and aligned AI systems as capabilities scale toward advanced autonomous intelligence. Research operates at the intersection of agent learning, alignment, and interpretability, with the goal of developing the scientific foundations required for trustworthy AI systems.
Key research areas include multi-agent reinforcement learning, continual learning and adaptive agents, alignment strategies and behavioral control methods, mechanistic interpretability and model transparency, information-theoretic approaches, foundation models for structured and tabular domains, and open research infrastructure for alignment experimentation. The lab publishes in leading venues such as ICML, ACL, IJCNN, and WWW.
Key research areas include multi-agent reinforcement learning, continual learning and adaptive agents, alignment strategies and behavioral control methods, mechanistic interpretability and model transparency, information-theoretic approaches, foundation models for structured and tabular domains, and open research infrastructure for alignment experimentation. The lab publishes in leading venues such as ICML, ACL, IJCNN, and WWW.
- Industry
- Technology
- Company Size
- 500+
- Website
- lexsilabs.com
🚀 Boost your chances
Skip the queue
Contact the recruiter directly at Lexsi Labs and follow up personally — most applicants never do.
Browse Recruiter DatabaseFree trial · 40 contacts · ₹0
Job Details
- Type
- Full time
- Level
- Mid-level
- Experience
- 2–5 years
- Location
- Bangalore, India (Hybrid)
- Work Mode
- Hybrid
- Category
- AI / ML
Share this Job
Recruiter Database
Want to stand out? Talk to the recruiter directly.
Most applicants never hear back. Our Recruiter Database gives you direct email access to the people making hiring decisions — so you can follow up personally and actually get noticed.
- Recruiter name, company & direct email address
- Sourced from active job postings across top companies
- Free trial — 40 contacts, no credit card needed