This Software Engineering III position at Morgan Stanley focuses on building and deploying AI Agents at scale, partnering with teams in Advanced Analytics, Machine Learning, and Gen AI. The role requires expertise in developing autonomous systems that utilize LLMs and reasoning models, ensuring robust architecture and implementation. The individual will work in a dynamic environment, collaborating with global teams to drive innovation and improve business solutions. The position emphasizes the importance of knowledge-sharing and effective communication within the team.

• 2+ years of experience in building GenAI solutions and supporting components design.
• Mastery of agent orchestration frameworks like LangChain, LangGraph, CrewAI, and Microsoft's AutoGen.
• Deep expertise in LLM APIs such as OpenAI and Anthropic, along with prompt engineering skills.
• Ability to implement complex memory systems, including vector databases and RAG pipelines.
• Proficiency in integrating external APIs and managing error handling for model outputs.
• Expert-level knowledge of Python, with familiarity in FastAPI, Node.js, or Go.
• Understanding of the applied Machine Learning lifecycle and MLOps.

• Act as a hands-on engineer to build and deploy AI Agents at scale.
• Evaluate state-of-the-art ML and Gen AI technologies to prototype solutions.
• Design, implement, and operationalize scalable data flows for AI Agents.

• Morgan Stanley offers extensive benefits that support employees’ careers, health, finances, and families, including top-tier medical coverage, mental health support, generous parental leave, fertility and family-building benefits, and robust retirement and stock purchase plans. Employees also gain access to continuous learning and networking opportunities, volunteer and giving programs aligned with the firm’s values, and hundreds of lifestyle perks like discounted products, cultural and entertainment tickets, and commuter savings.