Senior AI Engineer – LLMs, Agentic AI

This is a fully remote position, open to applicants in Colombia.

📋 Description

• Construct and sustain MCP servers, tool definitions, and context management functionalities.

• Design and execute workflows for intent evaluation, classification, and routing.

• Integrate Anthropic and OpenAI models into operational settings.

• Oversee prompt versioning, fallback strategies, and optimization of LLM performance.

• Create and uphold evaluation frameworks to assess model quality and operational performance.

• Work closely with software engineers and AI experts to deliver AI solutions that are ready for production.

• Engage in architecture discussions and contribute to the design of AI platforms.

• Continuously enhance AI systems through experimentation, optimization, and adherence to engineering best practices.

⛳️ Requirements

• A Bachelor’s Degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related discipline is preferred, or equivalent professional experience.

• Excellent proficiency in Python and familiarity with software engineering best practices.

• Strong SQL capabilities with experience in cloud data warehouses.

• Practical experience in building production-grade LLM and agentic AI applications.

• Experience in implementing tool calling, MCP servers, context management, and multi-step orchestration.

• Familiarity with integrating hosted LLM APIs such as Anthropic and OpenAI into production environments.

• Experience in prompt engineering, prompt versioning, fallback strategies, and cost/latency optimization.

• Knowledge of designing intent classification and routing solutions for natural language applications.

• Experience in developing conversational AI solutions or multi-API orchestration workflows.

• Proficiency in developing LLM evaluation methodologies and working within existing codebases.

• Strong skills in collaboration, communication, and problem-solving.

• Proficient in professional English.

• Nice to Have: Experience in deploying, fine-tuning, and evaluating open-source models using Hugging Face.

• Experience with GPU acceleration and inference optimization.

• Familiarity with implementing MLOps practices, including CI/CD, observability, and reproducible pipelines.

• Experience with vector databases and Retrieval-Augmented Generation (RAG).

• Applied experience in NLP.

• Experience in building client-facing AI products.

• AWS certification.

🏝️ Benefits

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