Staff Engineer, Agent Systems

Jobtailor; Región Centro; Presencial; MXN 1.200.000 - 2.100.000; Jornada completa

Descripción de la vacante

Jobtailor is seeking a senior engineer to design and own the agent systems platform, including retrieval, orchestration, tool integration, and evaluation, to deliver a cohesive production-grade solution.

You will build robust RAG pipelines grounded in CargoSprint data, craft multi-step workflows with LangGraph or LangChain, and connect agents to production systems like Salesforce, HubSpot, and Postgres. You will drive observability and reliability across the stack.

Formación

• Experience building production-grade distributed systems.
• Proven ownership of architectural decisions and lessons learned.
• Excellent English communication across product, engineering, and staff levels.
• Willingness to travel to Guadalajara, MX as needed.
• Expert-level Python coding in production environments.
• Deep RAG system design experience with retrieval pipelines and evaluation.
• Experience with LangGraph, LangChain, or equivalent for multi-step agent workflows.
• Strong knowledge of vector databases and search ecosystems (pgvector, Pinecone, Weaviate).
• Frontend/backend integration via FastAPI and related tooling; production-grade design.
• Observability, tracing, logging, and alerting in a live system.
• DevOps fundamentals including Docker, Kubernetes, and CI/CD.

Responsabilidades

• Design and own the agent systems architecture — retrieval, orchestration, tool integration, and evaluation.
• Build RAG pipelines grounded in operational data, including indexing, chunking, embeddings, retrieval, and freshness.
• Create orchestration patterns for multi-step workflows with failure handling and degradation.
• Develop the tool layer connecting agents to production systems (Salesforce, HubSpot, Postgres, internal APIs) with robust error handling.
• Instrument systems with tracing, latency dashboards, and retrieval quality metrics.
• Establish reusable agent primitives and engineering patterns to accelerate future work.
• Collaborate with engineers building agents to review architectures and raise quality.
• Travel to the Guadalajara office to work with operational teams on real workflows.
• Leverage AI coding tools to accelerate development and set standards.

Conocimientos

Python

Distributed systems

RAG systems

English communication

Architectural decisions

Production-grade software

Problem-solving

Travel willingness

Code reviews

Herramientas

LangGraph

LangChain

FastAPI

Docker

Kubernetes

CI/CD

pgvector

Pinecone

Weaviate

Descripción del empleo

Responsibilities

• Design and own the agent systems architecture — retrieval, orchestration, tool integration, and evaluation — as a coherent, production‑grade platform
• Build RAG pipelines that ground agents in real CargoSprint data: indexing strategies, chunking, embedding models, retrieval evaluation, and freshness maintenance
• Design orchestration patterns for multi‑step agentic workflows using LangGraph or equivalent — with explicit attention to failure modes, non‑determinism, and graceful degradation
• Build and maintain the tool and integration layer that connects agents to production systems — Salesforce, HubSpot, Postgres, internal APIs — with the error handling and retry logic that production demands
• Instrument everything: distributed tracing, latency dashboards, retrieval quality metrics, LLM output evaluation pipelines
• Establish reusable agent primitives and internal engineering patterns so the team builds the next agent faster and more reliably than the last one
• Partner with the engineers building individual agents to review architectures, catch design mistakes early, and raise the overall quality bar
• Travel to CargoSprint's Guadalajara office as needed to work directly with the operational teams whose workflows the agents are being built around
• Use AI coding tools to accelerate your own development and set the standard for how the team works with them

Requirements

• 8+ years of engineering experience, with meaningful time spent building systems that run reliably under real production load
• A track record of technical decisions you made, owned, and lived with — including the ones that turned out to be wrong and what you did about them
• Strong business judgment — you understand that a technically elegant agent nobody uses is a failure. You can read a workflow, identify the real cost, and design for adoption, not just correctness.
• Excellent communication in English — you can explain a retrieval architecture to a product manager and a vector indexing strategy to a staff engineer, and you know which explanation to give in which room
• Willingness to travel to CargoSprint's Guadalajara, Mexico office as needed — the workflows you are designing systems for live there, and understanding them firsthand matters
• Expert‑level Python — idiomatic, well‑tested, production‑grade. You write code that the next engineer can understand and extend.
• Deep RAG system design experience — you have designed and operated retrieval pipelines in production: chunking strategies, embedding model selection, hybrid search, re‑ranking, context window management, and retrieval evaluation. You know the failure modes intimately.
• Agent orchestration architecture — LangGraph, LangChain, or equivalent; you have designed multi‑step agentic workflows with tools, memory, branching logic, and human‑in‑the‑loop patterns that are predictable under real usage
• LLM integration and prompt engineering — you understand how to structure prompts for reliability, how to version and evaluate them, and how to manage the gap between model capability and production behavior
• Vector databases and search infrastructure — pgvector, Pinecone, Weaviate, or equivalent; you know when to use dense vs. sparse retrieval and how to build an evaluation harness to measure retrieval quality
• FastAPI and backend service design — you build the infrastructure your agent systems run on with the same rigor as the systems themselves
• Observability and production operations — distributed tracing, structured logging, alerting, LLM‑specific evaluation pipelines; you know what good looks like before something breaks
• DevOps fundamentals — Docker, Kubernetes, CI/CD; you own what you ship all the way to production.