Senior AI Engineer, LLMs, Agentic AI

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

📋 Description

• Construct and oversee MCP servers, along with tool and resource definitions and context management functionalities.

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

• Coordinate the resolution into appropriate API and data-source calls, including aggregation from multiple sources.

• Integrate Anthropic and OpenAI models within production settings.

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

• Design and sustain evaluation frameworks to assess model quality and performance in production.

• Write SQL queries for model inputs and outputs to facilitate evaluation and monitoring.

• Support the backend functionality of the chat/MCP interface.

• Trace system behavior and implement safe, incremental modifications in a partially documented codebase.

• Collaborate with software engineers and AI experts to deliver production-ready AI solutions.

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

• 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.

• Strong command of Python and best practices in production backend software engineering, including APIs, async I/O, typing/schema validation, error handling, and testing.

• Proficient in SQL with cloud data warehouses; experience with Snowflake is preferred.

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

• Must have personally developed and deployed an MCP server in a production environment used by other users or systems.

• Experience in constructing and deploying MCP servers, encompassing tool and resource definitions, context management, and multi-step orchestration.

• Familiarity with MCP transports, including stdio and Streamable HTTP.

• Understanding of authentication and authorization patterns for remote servers, including OAuth/OIDC, scoped access, and resource-level access.

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

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

• Experience in designing solutions for intent classification and routing for natural language applications.

• Background in building conversational AI solutions or workflows that orchestrate multiple APIs.

• Experience in developing methodologies for LLM evaluation.

• Experience working within a partially documented, brownfield Python codebase.

• Strong collaboration, communication, and problem-solving abilities.

• Capability to explain personal technical work in detail under sustained technical questioning.

• Proficient spoken English (B2+) for real-time technical discussions with stakeholders based in the US.

• Experience in creating production AI applications using Python and LLM technologies.

• Hands-on experience enhancing a production Python codebase with significant features.

• Experience in designing and deploying solutions for conversational AI or agentic AI.

• Strong expertise in prompt engineering, LLM integrations, and evaluation methodologies.

• Nice-to-have: Familiarity with Hugging Face, GPU acceleration, MLOps, CI/CD, observability, reproducible pipelines, vector databases, RAG, applied NLP, client-facing AI products, and AWS services.

🏝️ Benefits

• Availability for remote work.

• Contractor model.

• Opportunity to work on production-grade LLM applications and agentic AI systems.

• Collaborative, lightly-managed team environment.

• Exposure to modern AI, cloud, data, and software engineering technologies.

• Opportunities for learning and ownership.

• An AI-native organization dedicated to meaningful, scalable solutions.