The Generative AI Technology team is a group of skilled professionals who are responsible for conceptualizing and developing the firm’s Generative AI efforts, in particular, the firm’s Generative AI platform. The team works closely with business stakeholders and development teams across Technology and the business to deploy innovative AI technology that can transform the firm’s operations.

What you’ll do

As an AI Engineer you will be responsible for designing, prototyping, deploying, and optimizing solutions while interacting with proprietary and open-source large language models (LLMs) to offer best-in-class capabilities to help drive adoption and integrate GenAI into applications and operations across the firm.

Specifically, you will:

• Architect, build, maintain, deploy, and support the internal GenAI platform (API/SDK’s, services, platform backend, integration with third-party models, integration with third-party vendors, etc.) 
• Design and build advanced GenAI plugins and services that streamline workflows and develop novel solutions to tackle complex challenges
• Conduct code reviews and PR reviews for contributions from within the team and from the firm’s inner source contributors
• Collaborate with our DevOps team to develop and maintain efficient CI/CD pipelines and processes, enhancing our development lifecycle
• Collaborate with our Cloud Engineering team to build and maintain a multi-cloud platform offering and leverage model offerings across multiple cloud providers, while adhering to industry best practices
• Collaborate with our research, product, data and UI/UX teams to ensure requirements are being met in the platform build-out
• Collaborate on design and implementation of best practices for Vector DB architecture, including data modeling, entitlements, indexing, and query optimization
• Stay ahead of the curve in generative AI and LLMs and collaborate with our research team to ensure that we are offering capabilities on the platform in a timely manner
• Produce clear and detailed design and technical documentation for our APIs, features, tools, and other platform capabilities, ensuring transparency, accessibility, and ease of use

What’s required

• Bachelor's degree in computer science, artificial intelligence, machine learning, or related field
• 2+ years of experience working with LLMs, Natural Language Processing (NLP), and/or prompt engineering
• 5+ years of industry experience in Python development
• Strong experience designing SDKs and REST APIs for integrating with internal business applications and third-party vendors
• Strong experience with system architecture design and deploying scalable, reliable, and thoroughly tested systems in business-critical production environments
• Strong tactical and strategic planning skills, with a keen eye for detail, and a focus on on-time and in-scope execution
• Experience with FastAPI, Pydantic, SQLAlchemy, Pandas, Poetry
• Experience with integration of cloud provider services including Azure OpenAI services, AWS Bedrock, or GCP Vertex
• Familiarity with Datadog, Alembic, PostgresSQL, Celery, AWS, Redis, and Jinja
• Familiarity with DevOps tools such as Jenkins, GitHub Actions, Artifactory, Helm
• A team player who can lead by example, handle changing priorities and explain technical concepts to senior and non-technical stakeholders
• Commitment and adherence to the highest ethical standards