Senior Software Engineer ( AI Platform )

Eligibility Notice This position is only open to candidates who are Mexican citizens currently residing in Mexico. Applications from candidates who do not meet this legal and operational requirement will not be considered. We appreciate your interest and encourage you to apply to roles that match your location.

Nexaminds is looking for a Senior Software Engineer – AI Platform to design and scale our next-generation internal AI capabilities. In this role, you will help build the foundational infrastructure and developer tools that enable engineering teams across the organization to efficiently deploy, monitor, and optimize intelligent cloud services.

Location: MEXICO

Qualifications we are looking for:

• 5+ years of software engineering experience, with Python as your primary programming language for enterprise solutions.

• 2+ years building production LLM systems, including hands-on experience with inference optimization, RAG, agentic patterns, or AI infrastructure.

• Dual-Language Fluency: Deep expertise in Python paired with working proficiency in C#/.NET to ensure seamless platform interop with .NET application teams.

• Agentic Frameworks: Strong hands-on experience with frameworks such as Semantic Kernel, LangGraph, LangChain, or custom-built agent orchestration runtimes.

• RAG Architecture: Production experience with advanced chunking strategies, embedding models, vector search, retrieval quality, and debugging complex RAG failure modes.

• Azure AI Ecosystem: Practical experience with Azure AI Foundry / Azure OpenAI, including model deployment, API integration, and cloud observability tooling.

• Platform & SDK Design: Proven track record building internal platforms, polyglot SDKs, or reusable libraries that abstract technical complexity for other engineers.

• AI Observability & Costs: Strong grasp of tracking token usage, latency, granular cost attribution, and distributed tracing across asynchronous workflows.

Nice to have:

• TypeScript experience for SDK expansion and frontend tooling work.

• Model Context Protocol (MCP) server development and agent tool ecosystem integration.

• Automated Eval framework experience (LLM-as-judge, rubric-based scoring, regression testing pipelines).

• AI governance execution (RBAC for model access, content filtering, PII redaction, prompt injection defense).

• Infrastructure deployment via Azure Container Apps and Terraform provisioning.

• Familiarity with AI regulatory frameworks (NIST AI RMF, ISO/IEC 42001).

Job duties:

• Design and build a core LLM gateway handling model routing, prompt versioning, fallback logic, per-team cost attribution, rate limiting, and semantic caching.

• Build and operate RAG pipelines, embedding services, and vector search infrastructure (Azure AI Search) for company-wide consumption.

• Develop the agentic runtime infrastructure, managing agent definitions, tool registration, state management, multi-step orchestration, and human-in-the-loop hooks.

• Design multi-agent coordination patterns using A2A protocol, Semantic Kernel agents, or equivalent frameworks.

• Build comprehensive AI observability and tracing pipelines to log prompts/responses, monitor latency, and track multi-agent workflow paths.

• &