Microsoft Security aims to make the world a safer place by reshaping security and empowering users, customers, and developers with a security cloud that protects them with end-to-end, simplified solutions. The Generalized Agents team is developing advanced agentic AI solutions, including RL fine-tuning of LLMs, to build intelligent systems that adapt, reason, and act autonomously, anticipating future technological needs and integrating AI capabilities into the product ecosystem to address today's challenges and lay the foundation for the next generation of applied AI and data science.
Requirements
- 2+ years of experience with LLMs and open-source GenAI frameworks, such as LangChain, LlamaIndex, Haystack, or equivalents (e.g., Transformers, AutoGen, DSPy), including agent-based orchestration, prompt engineering, retrieval-augmented generation (RAG), and fine-tuning and evaluation.
- Proficiency in writing production-quality software code in one or more modern programming languages (Python, C-Sharp)
- 5+ years experience developing software systems end-to-end, from design to implementation.
- 2+ years experience in shipping at least 2 large scale ML/AI-based services or applications on cloud platforms (Azure, AWS, GCP, etc.)
- coding in languages including C-Sharp AND Python
Responsibilities
- Architect, design, and implement training and solution pipelines for complex agentic AI systems, including building tech preview prototypes.
- Integrate RL-fine-tuned LLM based research prototypes into production-level platforms.
- Collaborate and drive common design with senior technical staff of Microsoft Sentinel Graph, Copilot for Security and other Microsoft Security products
- Act as a catalyst in accelerating the team’s transition to an AI-first mindset and development approach.
- Serve as a thought leader in architecting advanced AI systems and agentic AI solutions with RL-fine-tuned LLMs.
Other
- Ability to meet Microsoft, customer and/or government security screening requirements are required for this role.
- Microsoft Cloud Background Check: This position will be required to pass the Microsoft Cloud Background Check upon hire/transfer and every two years thereafter.
- Embody our culture and values
- passionate about the latest AI advancements, has a high-level dedication to team success, drives and implements high-quality code, and is willing to take on a challenge of collaborating with a team of world-class applied AI researchers.
