AI Developer: LLM Workflows & Production Systems

Willis Towers Watson; Ciudad de México; Presencial; MXN 900.000 - 1.200.000; Jornada completa

Descripción de la vacante

Willis Towers Watson is seeking an AI-enabled backend engineer in Mexico City. You will design, implement, and test multi-step agent workflows, integrating LLMs with enterprise APIs and internal systems.

You will ensure reliability with retries, tool-chaining, and memory retrieval using vector databases, while deploying AI services to production and monitoring performance. The role requires 2+ years in backend or service-based development (C# or Python), 1+ year with large language models, and

Formación

• Minimum 2 years’ experience developing backend or service-based systems using C# and/or Python.
• At least 1 year of hands-on experience with large language models, prompt engineering, or AI-enabled systems.
• Strong analytical and debugging skills across APIs, data flows, and AI system behavior.
• Ability to communicate technical decisions to technical and non-technical stakeholders.
• Learning aptitude in a rapidly evolving tech environment.
• Programming: C#, Python (production services, async workflows, automated testing).
• Cloud Platform: Azure (compute, storage, identity, deployment pipelines).
• LLM Integration: Claude and/or OpenAI APIs (prompting, tool calling, rate limits, error handling).
• Agent Orchestration: Azure AI Foundry, Microsoft Agent Framework; LangGraph or LangChain as alternatives.
• Vector Databases: Pinecone or equivalent (indexing, retrieval, relevance tuning).
• APIs & Integration: RESTful APIs, enterprise authentication, service-to-service integration.
• Observability: Production logging, metrics, and tracing.

Responsabilidades

• Design, build, and test multi-step agent workflows using patterns like ReAct, planner-executor, and tool-chaining.
• Integrate LLMs with enterprise APIs and internal systems with robust retry and error handling.
• Implement tool calling, function orchestration, and compensating actions for stability.
• Design human-in-the-loop controls including approvals and escalations.
• Collaborate with product managers and stakeholders to translate requirements into designs.
• Develop, maintain, and version prompt logic and supporting docs.
• Build and manage agent memory and retrieval using vector databases and RAG.
• Deploy AI services to production; monitor logs, traces, and metrics to resolve issues.
• Contribute to test coverage, runbooks, and incident response with QA/ops.
• Support continuous improvement of system reliability and performance.

Conocimientos

Backend development

Python

C#

LLM systems

Debugging

API integration

Communication

Educación

Bachelor's degree in CS or related field

Herramientas

Azure AI Foundry

Microsoft Agent Framework

LangGraph

LangChain

Pinecone

OpenAI API

Descripción del empleo

Willis Towers Watson is seeking an AI-enabled backend engineer in Mexico City. You will design, implement, and test multi-step agent workflows, integrating LLMs with enterprise APIs and internal systems.

You will ensure reliability with retries, tool-chaining, and memory retrieval using vector databases, while deploying AI services to production and monitoring performance. The role requires 2+ years in backend or service-based development (C# or Python), 1+ year with large language models, and