Solutions Architect – Agentic Ai

Capmation Inc.; Xico; On-site; MXN 1,200,000 - 1,900,000; Full time

Job summary

Capmation Inc. is seeking a Solutions Architect to lead the design, development, and deployment of scalable agentic AI solutions for enterprise environments. You will drive hands-on engineering while providing technical leadership across teams and stakeholders.

The role requires senior technical vision, mentorship of engineers, and the ability to balance pragmatic delivery with strategic decisions in a fast-moving AI landscape.

Qualifications

• Must have 6+ years of software engineering experience with 3+ years in architect/lead roles and 2+ years building LLM-based apps.
• Proven track record designing end-to-end AI architectures for enterprise environments.
• Hands-on experience with LLM frameworks, vector databases, and API integration.

Responsibilities

• Lead end-to-end architecture of agentic AI solutions, integrating LLMs, RAG, AI agents, APIs and vector databases.
• Design, develop, and deploy AI apps and agent workflows while evaluating new AI frameworks and methodologies.
• Define guardrails and human-in-the-loop controls within multi-agent systems.
• Oversee integration of AI components with enterprise APIs, data platforms, and SaaS systems with strong security and observability.
• Define evaluation frameworks for LLMs and agents, including latency and cost considerations.
• Drive optimization of prompts, routing, caching and retrieval for cost efficiency.
• Own production health of AI workloads, incident triage and root-cause analysis.

Skills

LLM development

RAG pipelines

Agent orchestration

Python

API design

Cloud experience

Education

BS/MS in CS or related

Tools

LangChain / LangGraph

Semantic Kernel

LlamaIndex

CrewAI / AutoGen

Job description

The Role

We are seeking a Solutions Architect to join our Engineering Team. This role combines deep hands-on engineering capability in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and AI agents with technical leadership in designing, developing, and deploying scalable agentic AI solutions for enterprise environments.

The ideal candidate is a senior technical leader who can define end-to-end AI solution architecture, guide engineering standards, solve complex integration, retrieval, and orchestration problems, and support the delivery of secure, reliable, and cost-efficient AI applications in a fast-moving environment.

This position also requires strong collaboration and leadership skills. The Solutions Architect must work effectively with engineers, product stakeholders, clients, and delivery teams, while providing technical guidance, mentoring engineering teams, and driving high engineering quality. The ideal candidate should be proactive, pragmatic, and able to balance hands-on implementation with strategic technical decision-making.

Key Responsibilities

• Solution Architecture: Lead the architecture of agentic AI solutions end-to-end, combining LLMs, RAG pipelines, AI agents, APIs, and vector databases into scalable, secure, and maintainable systems
• Hands-on Engineering: Design, develop, and deploy AI applications and agent workflows, while leading evaluation and adoption of new AI frameworks, models, and methodologies to improve company standards
• Agent & RAG Design: Design multi-agent orchestration, tool/function calling, memory, and retrieval strategies (chunking, embeddings, hybrid search, reranking) with guardrails and human-in-the-loop controls built in by default
• Integrations: Lead the integration of AI components with enterprise APIs, data platforms, and SaaS/line-of-business systems, ensuring robust error handling, idempotency, security, and observability
• Testing & Evaluation: Define and enforce evaluation frameworks for LLM and agent outputs (accuracy, groundedness, hallucination rate, latency, and cost), including regression testing and automated quality gates
• Optimization: Drive performance and cost optimization through prompt engineering, model selection and routing, caching, token management, and retrieval tuning
• Operational Excellence: Own production health of AI workloads through tracing, monitoring, and LLMOps practices; lead incident triage and root-cause analysis for complex issues
• Responsible AI & Governance: Ensure solutions meet data privacy, PII handling, security, and responsible-AI requirements, aligned with company AI governance policies
• Cross Functional Collaboration: Partner with business ops, stakeholders, and clients to translate business requirements into AI solution designs and act as the intermediary between business operations and engineering
• Team Development: Provide technical guidance and mentor engineers at all levels while also leading training sessions, design and code reviews, providing constructive feedback, and aligning technical standards across the team

Soft Skills

• Business Acumen: Connect AI architecture decisions to business outcomes, anticipating impacts on cost, risk, and value, and providing decisions to maximize long-term value.
• Accountability: Accountable for the technical and delivery success of AI solutions or projects, taking ownership of outcomes across teams and addressing issues proactively rather than reactively.
• Communication: Communicate complex AI and architecture concepts clearly to both technical and non-technical audiences, aligning stakeholders, and enabling confident decision making.
• Judgement: Demonstrate judgment by making high-impact decisions, balancing innovation and short-term delivery with long-term sustainability, security, and escalating risks early.
• Collaboration: Drive alignment across multiple teams and disciplines by acting as a unifying technical leader, resolving cross-team friction.
• Curiosity: Maintain curiosity about the rapidly evolving AI landscape and emerging technologies, using that understanding to anticipate challenges, guide innovation, and continuously improve technical and delivery practices.

Required Qualifications

Experience: Over 6+ years of software engineering experience, including 3+ years in an architect or technical lead role and 2+ years building LLM-based applications, in the following:

Tech Stack

Generative AI & LLMs

• LLM platforms: Azure OpenAI, OpenAI, Anthropic, AWS Bedrock, Google Vertex AI
• Prompt engineering, structured outputs, function / tool calling
• Model selection, routing, and fine-tuning fundamentals

Agentic AI & Frameworks

• LangChain / LangGraph, Semantic Kernel, LlamaIndex
• Multi-agent frameworks: CrewAI, AutoGen, or equivalents
• Model Context Protocol (MCP) and agent-to-agent communication patterns
• Agent memory, planning, and human-in-the-loop workflows

RAG & Vector Databases

• Vector databases: Pinecone, Weaviate, Qdrant, pgvector, Azure AI Search
• Embedding models, chunking strategies, hybrid search, and reranking
• Document ingestion and data preparation pipelines

Languages & APIs

• Python (primary); C# / .NET or TypeScript a plus
• RESTful and GraphQL API design, JWT / OAuth2 authentication
• FastAPI, ASP.NET Core, or equivalent API frameworks

Cloud & Infrastructure

• Azure, AWS, or GCP cloud-native services
• Containers and orchestration: Docker, Kubernetes
• Serverless compute (Azure Functions, AWS Lambda)
• Secrets and identity management (Key Vault, Managed Identities)

Architecture & Patterns

• Agentic and RAG reference architectures
• Event-driven, domain-oriented microservices
• Resiliency patterns (retries, circuit breakers, fallbacks) for LLM calls
• Caching and cost-control patterns for AI workloads

DevOps & LLMOps

• CI/CD pipelines (Azure DevOps, GitHub Actions)
• Terraform or Bicep for Infrastructure as Code
• Prompt and model versioning, Git branching and pull request workflows

Testing & Evaluation

• LLM evaluation frameworks: Ragas, DeepEval, promptfoo, or equivalents
• Unit, integration, and API testing (pytest, Postman / Bruno)
• Guardrails and safety testing (content filtering, prompt-injection defense)

Observability & Operations

• LLM tracing: LangSmith, Langfuse, OpenTelemetry
• Application Insights, Log Analytics, or equivalent monitoring platforms

Must have:

• Proven experience designing, developing, and deploying LLM-based applications to production, including RAG pipelines and agentic / multi-agent workflows.
• Hands-on experience with AI frameworks such as LangChain / LangGraph, Semantic Kernel, or LlamaIndex, and with at least one major LLM platform (Azure OpenAI, OpenAI, Anthropic, AWS Bedrock).
• Strong experience with vector databases and retrieval design, including embeddings, chunking, hybrid search, and reranking.
• Deep proficiency in Python and solid API design and integration skills, building and securing RESTful services that connect AI components with enterprise systems.
• Track record leading solution architecture for enterprise-scale systems, including non-functional requirements, trade‑off analysis, and architecture governance.
• Experience defining evaluation, testing, and optimization strategies for AI applications (quality, latency, and cost).
• Cloud-native deployment experience on Azure, AWS, or GCP, including containers, CI/CD pipelines, and Infrastructure as Code.
• Demonstrated ability to provide technical guidance and mentor engineering teams.

Preferred Qualifications

• Experience with the Model Context Protocol (MCP) and building tool ecosystems for AI agents.
• Experience with LLMOps practices: prompt versioning, evaluation pipelines, and LLM tracing (LangSmith, Langfuse, OpenTelemetry).
• Background in Domain-Driven Design and event-driven architecture.
• Familiarity with AI governance and risk frameworks (NIST AI RMF, ISO/IEC 42001) and data privacy regulations.
• Experience with C# / .NET and Semantic Kernel in Microsoft-centric environments.
• Consulting or client-facing delivery experience, including discovery and whiteboard sessions.
• Cloud or AI certifications (e.g., Azure Solutions Architect Expert, Azure AI Engineer Associate, AWS Solutions Architect Professional).