AI Engineer Senior

Requirements

- Minimum 4 years of experience in software engineering, including at least 1 year working with Large Language Models (LLMs), AI integrations, or agentic AI solutions.

- Strong programming skills in Python;

experience with TypeScript and/or Go is an advantage.

- Proven experience developing and maintaining production-grade backend services and APIs (REST, gRPC).

- Hands-on experience integrating LLM platforms such as OpenAI, Anthropic, Google Gemini, or open-source models into business applications.

- Knowledge of structured outputs, tool/function calling, Model Context Protocol (MCP), and AI gateway implementations.

- Experience with agentic AI and orchestration frameworks such as LangGraph, LangChain, LlamaIndex, CrewAI, or Semantic Kernel.

- Solid understanding of Retrieval-Augmented Generation (RAG) architectures, including chunking strategies, embeddings, vector databases (Pinecone, Weaviate, pgvector), and retrieval methodologies.

- Experience working with cloud-native technologies, including AWS and/or GCP, Kubernetes, Terraform, event-driven architectures, and messaging platforms such as Kafka.

- Familiarity with LLM evaluation, monitoring, and observability tools such as LangSmith, Weights & Biases, or custom evaluation frameworks.

- Experience managing and supporting production environments, including monitoring, incident response, platform upgrades, and operational support.

- Ability to work effectively in fast-paced, ambiguous environments while delivering iterative solutions and ensuring end-to-end service reliability.

- Excellent written and verbal communication skills with the ability to explain technical concepts and trade-offs to non-technical stakeholders.

Preferred Qualifications

- Experience with enterprise AI platforms such as Glean, Anthropic Claude, OpenAI, Gemini Enterprise, or Claude Code.





- Experience building agentic automation solutions for business operations and enterprise workflows.

- Knowledge of vendor management, platform lifecycle management, and technology roadmap alignment.

- Contributions to open-source AI/ML projects.

- Experience with model fine-tuning, inference optimization, and AI performance tuning.

Activities to Perform

- Design, develop, deploy, and maintain agentic AI solutions that support and optimize business operations across multiple organizational functions.

- Build and enhance Enterprise AI architecture and infrastructure, including agent orchestration frameworks, tool integrations, RAG pipelines, and LLM inference services.

- Lead the full AI solution lifecycle, from proof of concept and prototyping through production deployment and ongoing optimization.

- Monitor, maintain, and improve AI systems running in production to ensure reliability, performance, and availability.

- Manage platform updates, upgrades, and deployments while ensuring business continuity and operational excellence.

- Collaborate with AI technology vendors and platform providers (e.g., Glean, OpenAI, Anthropic, Gemini Enterprise) to implement new features and maintain alignment with product roadmaps.

- Implement observability, evaluation, governance, and safety controls to ensure responsible and reliable AI system operation.

- Participate in architecture and design reviews, evaluating trade-offs related to scalability, cost, autonomy, security, and safety.

- Partner with cross-functional teams to identify business opportunities, develop AI-driven solutions, and deliver end-to-end implementations.

- Evaluate emerging AI models, frameworks, and agentic patterns to continuously improve enterprise AI capabilities.

- Own the operational health, reliability, and performance of deployed AI services and infrastructure.

- Troubleshoot incidents, optimize system performance, and ensure adherence to enterprise standards and best practices.

Location: Mexico / Hybrid

Language: English Advanced

📌 Data Scientist Python/R Sr (México)
🏢 SOFTTEK
📍 México