AI Engineer

Morgan Stanley is seeking an AI Engineer to join its Advanced Analytics, Machine learning and Gen AI Platform teams. This Software Engineering III (Director level) role focuses on building and deploying AI agents at scale using LLMs and reasoning models, with an emphasis on reliable agent performance, accuracy guardrails, and scalable platform architecture.

Based in New York, NY (onsite), the position supports technology and business roadmaps through hands-on engineering across agent orchestration, data flows, and cloud adoption.

Role Focus

• Build and deploy AI agents at scale to accelerate technology and business roadmaps
• Develop and improve agent accuracy guardrails, calibration scoring, and scalable architecture for data flows
• Operationalize distributed systems that support batch and real-time data ingestion, processing, storage, and access for AI agents

Responsibilities

• Act as a catalyst for building and deploying AI Agents at scale
• Evaluate state-of-the-art GenAI centric technologies and prototype solutions to improve platform architecture
• Design, implement, and operationalize distributed, scalable, and reliable data flows for AI agents in both batch and real-time modes

What You’ll Bring

• 2+ years of experience building GenAI solutions and supporting components design, architecture, development, and operationalization of agent orchestrations at scale
• Proficiency with multi-agent workflow frameworks including LangChain, LangGraph, CrewAI, and Microsoft AutoGen
• Deep expertise in LLM APIs such as OpenAI, Anthropic, and AWS Bedrock, along with prompt engineering (Chain-of-Thought) and fine-tuning for agent behaviors
• Ability to implement memory systems including vector databases (Pinecone, Weaviate) and RAG pipelines
• Experience integrating external APIs as agent tools, including function calling and error handling for malformed model outputs
• Expert-level Python (mandatory), often paired with FastAPI, Node.js, or Go
• Familiarity with Docker and Kubernetes for containerized deployment
• Ability to operate in a fast-paced, dynamic environment with limited supervision and to knowledge-share across team members
• Comfort managing time working with a global team on multiple initiatives
• Good written and verbal communication skills

Key Technologies

• LLMs/Reasoning models; LangChain; LangGraph; CrewAI; Microsoft AutoGen
• OpenAI; Anthropic; AWS Bedrock
• Chain-of-Thought; fine-tuning
• Vector databases: Pinecone; Weaviate
• Retrieval-Augmented Generation (RAG); function calling; error handling for malformed outputs
• Python; FastAPI; Node.js; Go
• Docker; Kubernetes; cloud adoption; agent orchestrations at scale

Compensation: USD 120,000 - 165,000 per year.

Experience: 2+ years.