We are seeking an innovative Agentic AI Forward Deployed Engineer (FDE) to build the next generation of autonomous AI systems.
In the Technology division, we leverage innovation to build the connections and capabilities that power our Firm, enabling our clients and colleagues to redefine markets and shape the future of our communities. This is a Lead Technical Product Owner position at Vice President level, which is part of the job family responsible for defining the product vision, prioritizing features, and ensuring the successful delivery of high-quality technical solutions.
What you'll do in the role:You will design multi-agent architectures that move beyond simple question-answering, enabling AI systems to break down problems, use external APIs, iterate through feedback loops, and operate independently to drive measurable business impact. You will enable transition of engineering teams from "developers" into "system architects". Instead of writing raw code, your focus will be on creating coding/testing agents and setting up "human-in-the-loop" or autonomous feedback harnesses and scaling these capabilities across the organization.
- Agent Architecture: Design and build multi-agent frameworks. Implement human-in-the-loop handoffs, logging, and guardrails to ensure agents comply with data protection and governance standards
- Agent-first engineering loop: Design and build agent skills, tools for desktop coding agents to improve engineering productivity. accelerate SDLC, reduce defects / rework and improve delivery quality through agentic workflows
- Evangelism & Coaching: Act as a trusted advisor, coaching engineering squads on effectively prompting, reviewing, and evaluating agent outputs. Drive enterprise AI adoption safely
- Hands-on programming to develop high performance code, implement application frameworks and develop prototypes to showcase new technology opportunities
What you'll bring to the role:- Overall experience between 7-12 years. Minimum 3 years in a role as Lead Engineer/Technical Architect designing for Distributed applications, Microservices architecture, Fault tolerance and recovery, Performance Engineering, Scaling, Low latency application design, Asynchronous programming
- Languages - Proficient in atleast one of Java or C# or Typescript/ReAct. Intermediate level Python
- Infrastructure - Comfortable shipping production grade systems on Hybrid cloud infra (Docker, K8s, AWS or Azure).
- AI Foundational: LLM fundamentals (encoder, decoder, and encoder-decoder models; fine-tuning vs. prompt-tuning vs. LoRA); Prompt engineering (zero-shot, few-shot, and chain-of-thought prompting; prompt testing and optimization); Vector databases (for embedding storage and similarity search); Embedding models (selection, generation, and dimensionality considerations).
- Agentic SDLC Harness: Design specialized SDLC agent harness loops (requirements, architecture, coding, and testing agents) and manage the interaction and context-sharing between them. Platform Integration (Embed agentic workflows natively into the existing developer ecosystem, CI/CD pipelines, version control, and test harnesses).
- Copilot/Open AI Codex/Claude Code: Leverage hands-on familiarity with Copilot/OpenAI Codex or Claude Code to optimize model prompting, tool usage, context construction, developing custom skills and system prompts to improve task solve rates
- LangGraph/OpenAI SDK/Claude SDK: Build autonomous AI agents with Conversational state, Tool calling, Sub agent orchestration
Secondary Skills- Agentic AI: Autonomous agent concepts (multi-step reasoning, goal decomposition, self-reflection loops, and replanning strategies); Tool-oriented execution (agents calling APIs, executing scripts, interacting with knowledge bases, or triggering workflows); Safety and governance (guardrails, grounding, hallucination prevention, and ethical AI use); Agent evaluation (reasoning accuracy, success/failure patterns, Efficiency metrics and Evaluation metrics such as accuracy, F1-score, or perplexity); MCP server concepts (architecture for agent communication and orchestration, request/response flows, streaming data, multi-agent coordination, and contextual state management); Agentic AI architecture internals (planner, executor, memory store, tool registry, event loop, orchestration layers, schedulers, task prioritization, failure recovery, and multi-agent collaboration patterns).
- RAG: RAG architecture (retrieval pipelines, context injection, and grounding of LLM outputs); document chunking and indexing (splitting strategies, token limits, and indexing performance); Query processing (rewriting, filtering, and ranking retrieved documents); Evaluation and latency optimization (measuring retrieval accuracy and reducing end-to-end response time).
WHAT YOU CAN EXPECT FROM MORGAN STANLEY: At Morgan Stanley, we raise, manage and allocate capital for our clients - helping them reach their goals. We do it in a way that's differentiated - and we've done that for 90 years. Our values - putting clients first, doing the right thing, leading with exceptional ideas, committing to diversity and inclusion, and giving back - aren't just beliefs, they guide the decisions we make every day to do what's best for our clients, communities and more than 80,000 employees in 1,200 offices across 42 countries. At Morgan Stanley, you'll find an opportunity to work alongside the best and the brightest, in an environment where you are supported and empowered. Our teams are relentless collaborators and creative thinkers, fueled by their diverse backgrounds and experiences. We are proud to support our employees and their families at every point along their work-life journey, offering some of the most attractive and comprehensive employee benefits and perks in the industry. There's also ample opportunity to move about the business for those who show passion and grit in their work.
To learn more about our offices across the globe, please copy and paste into your browser.
Morgan Stanley is an equal opportunity employer committed to building and maintaining a workforce that is diverse in experience and background. Our recruiting efforts reflect our strong commitment to a culture of inclusion, where individuals are hired, developed, and advanced based on their skills and talents.
Our workforce reflects a broad cross-section of the global communities in which we operate, bringing a variety of backgrounds, talents, perspectives, and experiences.
For more information, please visit:
Never miss an opportunity! Create an alert based on the job you applied for.