Principal AI Engineer - Remote Work | REF#302952

BairesDev; Palo Alto (CA); On-site; MXN 2,376,000 - 3,394,000; Full time

Benefits offered by this job

100% remote work

Excellent compensation in USD or local

Hardware and software setup for home

Flexible hours

Paid parental leaves and holidays

Mentorship and growth opportunities

Job summary

BairesDev is seeking a Principal AI Engineer to set the technical direction and own the architecture of a major enterprise AI assistant serving thousands of employees. You will stay hands-on, making orchestration and retrieval decisions while guiding distributed teams and future hires.

You will shape the system from the ground up, ensure robust evaluation, and drive best practices in CI/CD, observability, and scalable AI services across the organization.

Qualifications

• 8+ years of experience with Python in production environments.
• Proven ownership of an agentic/LLM platform from architecture to operation.
• Deep expertise in LangChain and LangGraph, including multi‑agent orchestration.
• Strong experience with LLM evaluation strategies: LLM-as-judge, offline evals, golden datasets.
• Experience with retrieval augmented generation over structured and unstructured data.
• Proficiency with React and TypeScript.
• Experience with A2A communication patterns and service‑to‑service agent integration.
• Model gateway/routing with Bedrock or LiteLLM; LangSmith tracing and eval harnessing.
• Streaming over WebSockets using LangGraph API (or similar).
• CI/CD and observability for AI services, including SLOs and eval gates.
• Distributed systems, microservices, and REST/GraphQL on AWS.
• Advanced proficiency in English.

Responsibilities

• Set technical direction and own architecture for an enterprise-scale AI platform.
• Design multi-agent orchestration including skill invocation and routing across agents.
• Own retrieval strategy across structured and unstructured data sources.
• Build and evolve the evaluation harness to validate AI system behavior.
• Mentor distributed engineering teams and influence technical hiring decisions.

Job description

At BairesDev®, we've been leading the way in technology projects for over 15 years. We deliver cutting-edge solutions to giants like Google and the most innovative startups in Silicon Valley.

Our diverse 4,000+ team, composed of the world's Top 1% of tech talent, works remotely on roles that drive significant impact worldwide.

When you apply for this position, you're taking the first step in a process that goes beyond the ordinary. We aim to align your passions and skills with our vacancies, setting you on a path to exceptional career development and success.

Principal AI Engineer at BairesDev

In this role, you'll set technical direction and own the architecture for an enterprise AI assistant serving thousands of employees, where a central orchestrator routes to specialized agents across multiple business functions. Staying hands-on in code most of the time, you'll make the hard calls on orchestration design, retrieval strategy, and evaluation, defending your choices against alternatives rather than defaulting to whatever a framework suggests. This is your opportunity to shape how an enterprise-scale agentic system is built from the ground up, while mentoring distributed teams and carrying technical judgment on future hires.

What You'll Do

• Set technical direction and own architecture for an enterprise-scale agentic AI platform.
• Design multi-agent orchestration, including skill invocation and routing across specialized agents.
• Own retrieval strategy across structured and unstructured data sources.
• Build and evolve the evaluation harness used to validate AI system behavior.
• Mentor distributed engineering teams and guide technical hiring decisions.

What We Are Looking For

• 8+ years of experience in Python.
• Proven experience owning an agentic or LLM platform end to end in production, from architecture through operation.
• Deep expertise in LangChain and LangGraph, including multi-agent orchestration, state, and tool/skill invocation.
• Strong LLM evaluation strategy experience, including LLM-as-judge, offline evals, and golden dataset design.
• Experience with RAG over structured and unstructured sources.
• Experience with React and TypeScript.
• Experience with agent-to-agent communication patterns (A2A) and service-to-service agent integration.
• Experience with model gateway and routing such as Bedrock or LiteLLM.
• Experience with LangSmith tracing and eval harness construction.
• Experience with streaming over WebSockets using LangGraph API or similar.
• Background with CI/CD and observability for AI services, including SLOs and eval regression gates.
• Experience with distributed systems, microservices, and REST/GraphQL on AWS.
• Advanced proficiency in English.

Nice To Have

• Experience with MCP server and tool integration.
• Experience with vector database selection and tuning, including Pinecone, FAISS, Qdrant, or pgvector.
• Familiarity with graph analytics and generated data visualization.

How we do make your work (and your life) easier:

• 100% remote work (from anywhere).
• Excellent compensation in USD or your local currency if preferred
• Hardware and software setup for you to work from home.
• Flexible hours: create your own schedule.
• Paid parental leaves, vacations, and national holidays.
• Innovative and multicultural work environment: collaborate and learn from the global Top 1% of talent.
• Supportive environment with mentorship, promotions, skill development, and diverse growth opportunities.

Join a global team where your unique talents can truly thrive and make a significant impact!