Senior AI Engineer – LLMs & Agentic AI – ID #00362

Location: LATAM
Employment Type: Full-time

We are looking for a Senior AI Engineer with strong experience building production-grade LLM applications and Agentic AI systems.

The ideal candidate combines strong Python software engineering skills with hands-on experience designing, integrating, evaluating, and optimizing AI-powered applications. You will work on conversational experiences and intelligent workflows, leveraging modern LLM technologies, tool calling, context management, and multi-step orchestration.

This role is suited for an engineer who enjoys solving complex AI challenges and continuously improving production systems through experimentation, evaluation, performance optimization, and engineering best practices.

You will collaborate closely with software engineers and AI specialists to design and deliver scalable, reliable, and production-ready AI capabilities.

Requirements

• 5+ years of professional experience building production applications.
• Strong proficiency in Python and production-grade software engineering practices.
• Strong SQL skills and experience working with data warehouses.
• Hands-on production experience building LLM-powered applications, including agentic and tool-use patterns such as function calling and MCP.
• Experience integrating LLM APIs such as OpenAI and Anthropic Claude into production environments.
• Strong experience with prompt engineering, prompt management and versioning, fallback strategies, and LLM cost and latency optimization.
• Experience implementing tool calling, MCP (Model Context Protocol) servers, context management, and multi-step orchestration.
• Experience designing intent classification and routing solutions for natural language applications.
• Experience building conversational AI solutions or multi-API orchestration workflows.
• Experience developing LLM evaluation methodologies and frameworks.
• Experience working effectively within existing production codebases and architectures.
• Experience with AWS and broader cloud computing concepts, including services such as AWS Batch, ECS, Lambda, and SQS.
• Strong understanding of scalability, reliability, observability, and production engineering principles.
• Strong collaboration, communication, analytical, and problem-solving skills.
• Upper-Intermediate to Advanced English proficiency (B2+/C1).
• Availability to work remotely with reasonable overlap with business hours.

Nice to Have

• Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related field, or equivalent professional experience.
• 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 experience with Natural Language Processing (NLP).
• Experience building client-facing AI products.
• AWS certification or equivalent cloud expertise.

Responsibilities

• Design, build, and maintain MCP servers, tool definitions, and context management capabilities.
• Develop and maintain AI-powered workflows using LLMs, tool calling, function calling, and multi-step orchestration.
• Design and implement intent classification, evaluation, and routing workflows.
• Integrate OpenAI, Anthropic Claude, and other hosted LLM APIs into production applications.
• Develop and maintain effective prompt engineering, management, and versioning strategies.
• Implement fallback mechanisms and optimize LLM performance, latency, reliability, and cost.
• Design and maintain LLM evaluation frameworks to measure model quality and production performance.
• Analyze AI system behavior and continuously identify opportunities for improvement.
• Collaborate closely with software engineers, data professionals, and AI specialists to deliver production-ready solutions.
• Participate in architecture discussions and contribute to the design and evolution of AI platforms.
• Work within existing codebases and architectures while identifying opportunities for technical improvement.
• Contribute to the deployment and operation of AI workloads in AWS and cloud environments.
• Continuously improve AI systems through experimentation, evaluation, optimization, and engineering best practices.
• Help ensure AI solutions are scalable, maintainable, observable, secure, and suitable for production environments.

What Sets You Apart

• Strong hands-on experience building LLM-powered applications in production.
• Practical experience designing and deploying Agentic AI or conversational AI solutions.
• Deep understanding of prompt engineering, LLM integrations, tool calling, MCP, and evaluation methodologies.
• Strong software engineering mindset applied to AI systems.
• Experience balancing AI quality, reliability, latency, scalability, and cost.
• Solid understanding of cloud infrastructure and AWS services.
• Ability to work effectively with ambiguous and complex technical challenges.
• Strong autonomy and ownership.
• Excellent communication skills and the ability to explain technical concepts to different stakeholders.
• Upper-Intermediate to Advanced English proficiency (B2+/C1).

What We Offer

• Fully remote work environment.
• Opportunity to work on cutting-edge Generative AI, LLM, and Agentic AI initiatives.
• Exposure to modern technologies including MCP, RAG, vector databases, AI orchestration, and cloud infrastructure.
• Collaboration with distributed and international technical teams.
• An environment focused on experimentation, innovation, and technical ownership.
• Opportunity to design and build production-grade AI solutions with real-world impact.