AI Engineer - R01565292

Ovii's Interpretation of the Role

The AI Engineer will design, build, and deploy autonomous AI agents and multi‑agent workflows that power business functions. You’ll collaborate with product, operations, and business teams to turn LLM prototypes into production‑grade, cost‑effective solutions.

Role Snapshot

• Design and ship AI agents
• Build multi‑agent systems with LLMs
• Integrate agents into enterprise platforms
• Create RAG pipelines and prompt libraries
• Implement observability, guardrails, and monitoring
• Optimize latency, accuracy, and cost

Must-Have Requirements

• Python / PySpark
• Statistical analysis (Regression, T‑Test, Z‑Test)
• ML frameworks (TensorFlow, PyTorch, scikit‑learn, Keras, MXNet, CNTK)
• RAG, prompt engineering, vector databases, tool/function calling, workflow orchestration, memory management
• Cloud platforms (Google Cloud, AWS, Azure)
• Software engineering fundamentals for scalable backend/full‑stack applications
• software engineering
• AI/LLM application development

Nice-to-Have Signals

• Vertex AI, Gemini Enterprise, OpenAI APIs
• AI evaluation frameworks, observability, guardrails
• Google Workspace APIs, Slack integrations
• Fine‑tuning, model optimization, open‑source LLM deployment
• Multi‑agent coordination and autonomous decision‑making
• LangChain, LangGraph, CrewAI, Google ADK, AutoGen, Semantic Kernel
• CI/CD, Kubernetes, Docker
• Enterprise integration (APIs, microservices, event‑driven systems)
• production deployment of AI applications
• AI evaluation and observability
• startup or innovation environment experience

Work Setup

• Location: Guadalajara, Mexico
• Work mode: HYBRID
• Remote scope: UNSPECIFIED
• Employment type: Full-Time

Eligibility Gates

• Visa sponsorship: unknown

Not Specified in JD

• Salary range
• Visa sponsorship
• Remote eligibility
• Education requirement
• Certifications
• Relocation
• Notice period
• Travel
• Security clearance
• Coding test
• Portfolio
• GitHub
• Writing sample
• Cover letter

What You'll Likely Work On

• Design, build, and deploy AI agents and multi‑agent systems using modern LLM frameworks
• Develop RAG pipelines, prompt libraries, and memory‑management components for enterprise use cases
• Integrate agents with Google Workspace, Slack, CRM systems, internal APIs, and databases
• Evaluate and select foundation models from providers such as Gemini, OpenAI, Anthropic, and open‑source options
• Implement observability, guardrails, and monitoring to ensure reliable production performance
• Collaborate with product, operations, and business stakeholders to prototype, iterate, and scale solutions
• Optimize agent performance for latency, accuracy, reliability, and cost

Good Fit If You Have

• Enjoy rapid experimentation and solving ambiguous problems
• Strong communication with both technical and non‑technical stakeholders
• Builder mindset with ownership and execution focus
• Experience in fast‑paced startup or innovation environments