Senior Researcher - Self-Evolving Agentic Systems
India, Karnataka, Bangalore • Full-time
Posted 19d ago
Job Location
India, Karnataka, Bangalore
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Agent Engineer
About the job
Microsoft Research India is seeking a Senior Researcher to advance the state of the art in self-evolving agentic systems. These agents will move beyond fixed prompts and static policies to continuously improve through their own experience, learn from failures, and adapt while operating. The role involves designing reinforcement learning algorithms, reward signals, building environments, and evaluations, and translating research ideas into scalable systems. Collaboration with researchers and engineers across Microsoft is a key aspect, aiming to contribute to both the research community and products used by millions.
Responsibilities
- Lead research on self-evolving agents, including self-improvement loops, experience-driven learning, self-generated curricula, and automatic refinement of agent policies, tools, and memory.
- Design and apply reinforcement learning methods for LLM-based agents, including reward modeling, learning from verifiable and AI feedback, and credit assignment over long, multi-step tasks.
- Build scalable training and evaluation environments for agentic tasks such as coding, tool use, web and computer use, and knowledge work.
- Develop rigorous benchmarks and evaluation methods that measure agent capability, robustness, safety, and improvement over time.
- Form hypotheses, design experiments, and iterate quickly on model and agent performance.
- Publish research at top-tier venues and release open-source artifacts.
- Collaborate with research and product teams across Microsoft to move research advances into real-world systems.
- Mentor interns and early-career researchers.
Requirements
- PhD in Computer Science, Machine Learning, Mathematics, or a related technical field, or equivalent experience.
- 1+ years of software engineering or research experience.
- Experience with reinforcement learning and LLMs.
- Strong research track record in machine learning, computer systems, or a closely related area.
- Demonstrated ability to conduct independent research and communicate results through publications, prototypes, or other impactful outcomes.
- Ability to work effectively across disciplinary boundaries and collaborate with diverse research and engineering teams.
- Experience building and scaling large AI systems (preferred).
- Experience applying reinforcement learning to AI models and agents (preferred).
- Experience with reward modeling, reinforcement learning, or other post-training techniques (preferred).
- Hands-on experience building datasets for LLM, VLM, or multimodal model pre-training or post-training (preferred).
- Experience with synthetic data, model graders, reward signals, hard-example mining, active learning, or data-mixture optimization (preferred).
- Experience building feedback loops that connect evaluation, failure mining, data generation, and training (preferred).
- Experience with multimodal or agentic datasets, including text, web, GUI, tool-use, or interaction trajectories (preferred).
