Senior GenAI Engineer in Mexico at Jobgether

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior GenAI Engineer based in Mexico.

This role offers the opportunity to engineer and operate production-grade generative AI systems used by real customers. You will take LLM-powered capabilities from initial concept through development, deployment, monitoring, and continuous improvement. The position combines backend engineering with agentic AI, retrieval-augmented generation, evaluation, and production observability. You will work hands-on with technologies such as LangGraph, Azure OpenAI, Gemini, Claude, and modern cloud services. A major focus will be ensuring high answer quality while optimizing latency, reliability, and infrastructure costs. You will join a technically ambitious environment where your decisions can directly influence how AI-powered products are designed and operated at scale.

• Build and deliver LLM-powered features end to end, including agentic workflows, retrieval pipelines, and tool-calling capabilities using LangGraph.
• Develop production-ready FastAPI services with streaming, persistence, automated testing, and appropriate reliability standards.
• Establish and maintain evaluation datasets, regression suites, and LLM-as-a-judge mechanisms to measure answer quality and validate changes before production release.
• Optimize the context provided to models by transforming user questions into effective search queries, orchestrating multi-step research workflows, and improving retrieval and prompt strategies.
• Diagnose incorrect or low-quality responses by determining whether issues originate from retrieval, query formulation, context construction, prompting, or model behavior, and implement targeted improvements.
• Instrument and monitor AI workflows using tracing and observability tools such as Langfuse and Azure Application Insights.
• Investigate production issues using real execution traces and proactively improve system reliability, performance, and answer quality.
• Manage latency, token consumption, and infrastructure costs, including intelligent routing across different model sizes and model families through an AI gateway.
• Contribute to architectural and technical decisions across the GenAI platform while identifying opportunities to improve automation, scalability, and operational efficiency.
• Collaborate with engineering and product stakeholders, communicate technical findings clearly, and contribute to the continuous evolution of production AI capabilities.

• 5+ years of professional software engineering experience, with strong hands-on experience building and operating backend services, APIs, asynchronous systems, and automated tests.
• Demonstrated experience taking LLM-powered features from prototype to production and maintaining them in a live environment.
• Practical experience with agentic AI or orchestration frameworks, ideally LangGraph.
• Strong hands-on experience with Retrieval-Augmented Generation (RAG), including retrieval strategies, query optimization, context construction, and evaluation.
• Experience debugging production LLM systems using tracing, evaluation frameworks, latency analysis, cost monitoring, and quality metrics.
• Professional experience deploying and operating cloud-based services, preferably within Microsoft Azure.
• Strong Python development skills, ideally combined with FastAPI and experience building scalable AI-enabled backend services.
• Familiarity with technologies such as Azure OpenAI, Google Gemini, Anthropic Claude, FAISS, PostgreSQL, Docker or Podman, and related AI infrastructure.
• Experience with infrastructure-as-code tools such as Bicep is an advantage.
• Strong analytical thinking, problem-solving ability, and sound technical decision-making skills.
• Fluent English communication skills, with the ability to collaborate effectively in a distributed and multicultural environment.
• Proactive, open-minded, and creative approach, with a genuine interest in advancing AI capabilities and automation.
• Previous mentoring or technical leadership experience is considered a plus.

• B2B contract arrangement.
• 100% remote work.
• Long-term engagement and the opportunity to contribute to a live production LLM product.
• Hands-on exposure to modern generative AI and LLM technologies.
• Work with a contemporary technology stack spanning agentic AI, RAG, cloud infrastructure, observability, and backend engineering.
• Flexible working environment designed to support autonomy and effective collaboration.