AI Engineer
Backend Developer
Agentic Ai
Agentic Ai Orchestration
Ai Agent
Ai Agent Platform
Ai Engineer
Artificial Intelligence
Data Analysis
Data Architecture
Data Engineer
Data Engineering
Data Integration
Data Pipeline
Data Platform
Data Processing
Database
Engineer
Generative AI
Generative Ai Applications
Generative Ai Platform
Information Technology (IT)
Large Language Models
Machine Learning
Programming
Programming Language
Programming Languages
Rag Systems
Job Description
Join Morgan Stanley’s Advanced Analytics, Machine learning and Gen AI Platform teams as an AI Engineer (Software Engineering III, Director level) in New York, NY (onsite). In this role, you’ll help build and deploy AI agents at scale using LLMs and reasoning models, supporting technology and business roadmaps with practical, production-oriented engineering across agent accuracy guardrails, calibration scoring, and cloud-ready architecture.
Compensation: USD 120,000 - 165,000 per year. Experience: 2+ years.
What you’ll do
- Operate as a hands-on catalyst for building and deploying AI Agents at scale to accelerate technology and business roadmaps.
- Evaluate state-of-the-art GenAI technologies and prototype solutions to improve the organization’s architecture and platform.
- Design, implement, and operationalize distributed, scalable, and reliable data flows that ingest, process, store, and enable access to data at scale for batch and real-time use by AI agents.
What you’ll bring
- 2+ years of experience building GenAI solutions and supporting components across design, architecture, development, and operationalization of agent orchestrations at scale.
- Strong proficiency with agent orchestration frameworks, including LangChain, LangGraph, CrewAI, and Microsoft’s AutoGen for multi-agent workflows.
- Deep expertise in LLM APIs such as OpenAI, Anthropic, and AWS Bedrock, including prompt engineering (Chain-of-Thought) and fine-tuning for specific agent behaviors.
- Ability to implement complex memory and context systems, including vector databases (Pinecone, Weaviate) and Retrieval-Augmented Generation (RAG) pipelines.
- Proficiency integrating external APIs as agent tools, including function calling and error handling for malformed model outputs.
- Expert-level Python (mandatory), commonly paired with FastAPI, Node.js, or Go.
- Familiarity with Docker and Kubernetes for containerized deployment.
- Comfort working in a fast-paced and dynamic environment, with good written and verbal communication skills.
- Ability to work with limited or no supervision, share knowledge across team members, and manage time collaborating with a global team across multiple initiatives.
Key technologies you’ll work with
- LLMs and reasoning models, LangChain, LangGraph, CrewAI, Microsoft AutoGen
- OpenAI, Anthropic, AWS Bedrock
- Chain-of-Thought, fine-tuning, RAG, function calling
- Vector databases: Pinecone, Weaviate
- Python, FastAPI, Node.js, Go
- Docker, Kubernetes, and cloud adoption
Similar Jobs
