Director, Software Engineer

Morgan Stanley•Alpharetta, GA

7d•Hybrid

About The Position

Morgan Stanley Services Group, Inc. is seeking a Director, Software Engineer in Alpharetta, Georgia to integrate Large Language Models (LLMs) into existing applications to enhance user experience. This role involves designing, implementing, and optimizing LLM-based solutions ensuring production-grade quality. The engineer will develop APIs and middleware to facilitate seamless communication between LLMs and existing systems, and collaborate with cross-functional teams, including product managers, data scientists, and software engineers, to define requirements and deliver solutions. Responsibilities include monitoring, analyzing, and fine-tuning LLM performance using metrics and user feedback, and implementing security best practices and data privacy policies for LLM interactions. The role also requires staying updated with advancements in AI, NLP, and machine learning to continuously improve integration strategies. Key tasks include integrating GenAI capabilities into enterprise applications, designing end-to-end GenAI pipelines and autonomous or semi-autonomous agent workflows, creating structured prompts, templates, and reusable prompt-engineering frameworks for diverse business use cases, and designing and implementing GenAI agents capable of reasoning, planning, and executing actions across internal APIs, enterprise tools, and third-party services. Additionally, the role involves developing and maintaining tool registries enabling GenAI agents to securely interact with enterprise systems and data sources, implementing metrics, observability, tracing, and structured logging for GenAI workloads, and building rapid Proofs of Concept (POCs) to validate GenAI ideas, measure ROI, and scale successful prototypes into production-ready systems. Participation in Agile ceremonies, including sprint planning, retrospectives, and continuous improvement initiatives, as well as conducting code reviews, design reviews, and prompt-optimization sessions to maintain engineering quality, are also expected. Telecommuting is permitted up to 2 days per week.

Requirements

Requires a Bachelor’s in Computer Engineering, Computer Science, or a related field of study.
Requires five (5) years of experience in the position offered or as a Full Stack Developer, Software Engineer, AI Engineer, or a related role.
Requires five (5) years of experience with the following skills: Full stack development skills in Python, Java and JavaScript; Working with different tools of Adobe Marketing cloud including Adobe Experience Manager, Target and Campaign; RESTful API development and integration; GraphQL API to serve dynamic request on data; Backend development experience with Node.js and Nest.js; Frontend development experience with Angular and React; DevOps tools and practices for deployment and monitoring; Implementing Continuous Integration and Continuous Deployment (CICD) pipelines using Jenkins, Bamboo, and Docker; and Atlassian’s toolset, including JIRA, Confluence, Box, BitBucket, Git repository, SVN, and SourceTree.
Requires two (2) years of experience with the following skills: AWS Lambda; AWS Gateway API; AWS SDK and AWS CDK; LLM APIs including OpenAI, Azure OpenAI, and Hugging Face; Prompt engineering frameworks, GenAI agent frameworks including LangChain, LlamaIndex, and Semantic Kernel; Performing model fine-tuning, embeddings, and secure tool registries; Utilizing observability tools including TruLens, and W&B; OAuth2; SAML authentication; API gateways; Kubernetes Helm; Terraform; Prometheus; Grafana, and enterprise; AI safety and compliance practices.

Responsibilities

Integrate Large Language Models (LLMs) into existing applications to enhance user experience.
Design, implement, and optimize LLM-based solutions ensuring production-grade quality.
Develop APIs and middleware to facilitate seamless communication between LLMs and existing systems.
Collaborate with cross-functional teams, including product managers, data scientists, and software engineers, to define requirements and deliver solutions.
Monitor, analyze, and fine-tune LLM performance using metrics and user feedback.
Implement security best practices and data privacy policies for LLM interactions.
Stay updated with advancements in AI, NLP, and machine learning to continuously improve integration strategies.
Integrate GenAI capabilities into enterprise applications, including designing end-to-end GenAI pipelines and autonomous or semi-autonomous agent workflows.
Create structured prompts, templates, and reusable prompt-engineering frameworks for diverse business use cases.
Design and implement GenAI agents capable of reasoning, planning, and executing actions across internal APIs, enterprise tools, and third-party services.
Develop and maintain tool registries enabling GenAI agents to securely interact with enterprise systems and data sources.
Implement metrics, observability, tracing, and structured logging for GenAI workloads.
Build rapid Proofs of Concept (POCs) to validate GenAI ideas, measure ROI, and scale successful prototypes into production-ready systems.
Participate in Agile ceremonies, including sprint planning, retrospectives, and continuous improvement initiatives.
Conduct code reviews, design reviews, and prompt-optimization sessions to maintain engineering quality.