Senior AI Engineer (LLMs & Agentic AI)

Applaudo; Medellín; Remote; COP 445,590,000 - 604,730,000; Full time

Job summary

Applaudo is seeking a Senior AI Engineer to build production-grade LLM and agentic AI applications. You will own MCP server design, tool definitions, and context management within a remote, contractor role aligned with US EDT hours.

You will integrate hosted LLM APIs, manage prompt strategies, and optimize performance across multi-source orchestration. Strong English communication is required to collaborate with US-based stakeholders.

Qualifications

• Bachelor's degree or equivalent professional experience.
• Strong Python and backend service design for production.
• Experience with cloud data warehouses (Snowflake preferred).
• Hands-on production-grade LLM and agentic AI applications.
• Experience building MCP servers in production and orchestration.

Responsibilities

• Build and maintain MCP servers, tool and resource definitions, and context management capabilities.
• Design and implement intent evaluation, classification, and routing workflows across multiple sources.
• Integrate Anthropic and OpenAI models into production environments.
• Manage prompt versioning, fallbacks, and LLM performance optimization.
• Develop evaluation frameworks for model quality and production performance.
• Write SQL against model inputs/outputs for evaluation and monitoring.
• Support backend behavior of chat/MCP interface.
• Work within an existing partially documented codebase and implement safe changes.
• Collaborate with engineers and AI specialists to deliver production-ready AI solutions.
• Contribute to AI platform architecture discussions and design.

Skills

Python

Production backend

APIs

Async I/O

Typing/Schema validation

Error handling

Testing

SQL

Snowflake

MCP servers

Auth/OAuth

OpenAI/Anthropic

Prompt engineering

Routing/intents

Conversation AI

Multi-API orchestration

LLM evaluation

Brownfield codebases

Documentation/Explain work

English communication

Education

Bachelor's degree in CS/Software/AI/Data Science

Tools

Snowflake

OpenAI

Anthropic

Hugging Face

CI/CD

ECS/Lambda

Job description

You are a Senior AI Engineer passionate about building production-grade LLM applications and agentic AI systems. You thrive in collaborative environments where you design, implement, and optimize AI capabilities that power conversational experiences and intelligent workflows.

You enjoy solving complex AI challenges, integrating cutting-edge LLM technologies, and continuously improving production systems through experimentation, evaluation, and engineering best practices. You're comfortable making production design decisions autonomously within a small, lightly-managed team, and defending those decisions directly to engineering leadership.

Note: This role operates under a contractor model and requires availability to work in the U.S. Eastern Daylight Time (EDT).

You Bring to Applaudo the Following Competencies:

• Bachelor's Degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related field is desired, or equivalent professional experience.
• Strong proficiency in Python and software engineering best practices for production backend services (APIs, async I/O, typing/schema validation, error handling, and testing).
• Strong SQL skills working with cloud data warehouses (Snowflake preferred).
• Hands-on experience building production-grade LLM and agentic AI applications.
• Hands-on experience building and deploying MCP servers in production (server-side, consumed by other users or systems), including tool and resource definitions, context management, and multi-step orchestration.
• Understanding of MCP transports (stdio vs. Streamable HTTP) and authentication/authorization patterns for remote servers (OAuth/OIDC, 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/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 the correct API and data-source calls.
• Experience building conversational AI solutions or multi-API orchestration workflows.
• Experience developing LLM evaluation methodologies and demonstrated ability to reverse-engineer and work within a partially documented, brownfield Python codebase.
• Strong collaboration, communication, and problem-solving skills.
• Demonstrated ability to explain your own technical work in first-person depth under sustained technical questioning, clearly distinguishing what you personally built, what you contributed to, and what you only observed.
• Strong spoken English (B2+) to discuss technical scenarios live with US-based stakeholders.

Nice to Have:

• 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 (Batch, ECS, Lambda, SQS).

You Will Be Accountable for the Following Responsibilities:

• Build and maintain MCP servers, tool and resource definitions, and context management capabilities.
• Design and implement intent evaluation, classification, and routing workflows, including orchestrating resolution into the correct API and data-source calls, with aggregation 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, tracing behavior and making safe, incremental changes.
• Collaborate closely 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.

Qualifications

• Experience building production AI applications with Python and LLM technologies.
• Must have personally authored/built an MCP server deployed in production and used by other users or systems (not simply integrated, consumed, or built as a local proof of concept).
• Hands-on brownfield experience, adding significant features to a production Python codebase.
• Experience designing and deploying conversational AI or agentic AI solutions.
• Strong experience with prompt engineering, LLM integrations, and evaluation methodologies.
• Strong spoken English (B2+)

Additional Information

All your information will be kept confidential according to EEO guidelines.

About Us

We Are Engineered Different.

At Applaudo, talented people design, build, and scale meaningful, AI-powered solutions that create real business impact. As an AI-native organization, we collaborate across design, development, cloud, data, and artificial intelligence to turn ideas into scalable products that transform how companies operate, make decisions, and grow.

We are building a high-performance culture grounded in five values: Empowering Excellence, Collaborative Teamwork, Unsolicited Respect, Consistent Transparency, and Efficient Communication. These define how we work, how we support one another, and how we hold ourselves accountable.

Applaudo is a place for people who want to learn fast, take ownership, and work alongside strong teams they are proud to belong to. Joining us means being part of an organization that is evolving intentionally, investing in modern ways of working, and leading AI-native transformation at scale.