Senior AI Engineer (LLMs & Agentic AI)

Applaudo Studios

19h

About The Position

Applaudo is seeking a Senior AI Engineer to build and maintain production-grade LLM applications and agentic AI systems that power conversational experiences and intelligent workflows. The role focuses on MCP servers, intent classification and routing, integrations with hosted LLMs, evaluation frameworks, prompt management, and support for the backend behavior of the chat/MCP interface. The engineer will work within a partially documented production Python codebase, make safe incremental changes, and collaborate with software engineers and AI specialists on production-ready solutions and AI platform design. This position operates under a contractor model and requires availability to work in U.S. Eastern Daylight Time (EDT). The engineer is expected to make production design decisions autonomously within a small, lightly managed team and explain and defend those decisions to engineering leadership. A bachelor's degree in a relevant field or equivalent professional experience is desired.

Requirements

Experience building production AI applications with Python and LLM technologies.
Strong proficiency in Python and production backend software engineering practices, including APIs, asynchronous I/O, typing and schema validation, error handling, and testing.
Strong SQL skills working with cloud data warehouses; Snowflake is preferred.
Hands-on experience building production-grade LLM and agentic AI applications.
Must have personally authored or built an MCP server deployed in production and used by other users or systems; integrating or consuming an MCP server, or building a local proof of concept, does not meet this requirement.
Experience building and deploying MCP servers in production, including tool and resource definitions, context management, and multi-step orchestration.
Understanding of MCP transports (stdio and Streamable HTTP) and authentication and authorization patterns for remote servers, including OAuth/OIDC and scoped and resource-level access.
Experience integrating hosted LLM APIs such as Anthropic and OpenAI into production environments.
Experience with prompt engineering, prompt versioning, fallback strategies, and cost and latency optimization, with direct ownership of these concerns in production.
Experience designing intent classification and routing solutions for natural language applications, resolving user intent into appropriate API and data-source calls.
Experience designing and deploying conversational AI solutions or agentic AI systems, or building multi-API orchestration workflows.
Experience developing LLM evaluation methodologies.
Hands-on experience working in a partially documented, brownfield Python codebase and adding significant features to a production Python codebase.
Strong collaboration, communication, and problem-solving skills.
Ability to explain personal technical work in first-person detail under sustained technical questioning, distinguishing what was personally built, contributed to, or only observed.
Strong spoken English (B2+) for discussing technical scenarios live with U.S.-based stakeholders.
A bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related field is desired, or equivalent professional experience.

Nice To Haves

Experience deploying, fine-tuning, and evaluating open-source models using Hugging Face.
Experience with GPU acceleration and inference optimization.
Experience implementing MLOps practices, including CI/CD, observability, and reproducible pipelines.
Experience with vector databases and Retrieval-Augmented Generation (RAG).
Applied NLP experience.
Experience building client-facing AI products.
AWS experience with Batch, ECS, Lambda, and SQS.

Responsibilities

Build and maintain MCP servers, tool and resource definitions, and context management capabilities.
Design and implement intent evaluation, classification, and routing workflows, including resolving requests into the appropriate API and data-source calls and aggregating results across multiple sources.
Integrate Anthropic and OpenAI models into production environments.
Manage prompt versioning, fallback strategies, and LLM performance optimization.
Develop and maintain evaluation frameworks to validate model quality and production performance.
Write SQL against model inputs and outputs to support evaluation and monitoring.
Support the backend behavior of the chat/MCP interface.
Work within an existing, partially documented codebase by tracing behavior and making safe, incremental changes.
Collaborate with software engineers and AI specialists to deliver production-ready AI solutions.
Participate in architecture discussions and contribute to AI platform design.
Continuously improve AI systems through experimentation, optimization, and engineering best practices.