Postúlate en Kit Empleo: kitempleo.com.mx/empleo/57ez1y

OverviewSTAND 8 provides end-to-end IT solutions to enterprise partners across the United States and internationally, with offices in Los Angeles, New York, New Jersey, Atlanta, Mexico, India, and more.We are building AI-powered products that are transforming how enterprises manage talent acquisition and workforce operations.
Our flagship platform processes millions of records, orchestrates multi-model AI pipelines, and delivers real-time intelligence across voice, text, and structured data channels.ResponsibilitiesAs a platform engineer you will build production-grade APIs, data pipelines, and AI systems that enterprise clients depend on daily.
The scope includes bidirectional CRM syncs handling hundreds of thousands of records, real-time data enrichment pipelines, document intelligence systems, and AI-powered voice interactions at scale.
You will work directly with platform leadership and collaborate with a distributed team across the US, India, and Mexico.
For Mexico-based candidates, this role is a foundational hire for our AI Center of Excellence in Mexico, with the opportunity to help shape and grow the team.Required QualificationsCore Engineering Foundation (Non-Negotiable)5+ years Python in production environments with a track record of shipping software that real users and systems depend on.
Not notebooks, not prototypes.Strong API development – Deep experience building production APIs with FastAPI, Django, or equivalent.
Must understand API design patterns, async request handling, middleware, dependency injection, authentication, rate limiting, background tasks, error handling, and versioning.Data pipeline architecture – Hands-on experience building ETL/ELT pipelines, bidirectional data syncs, data transformation layers, and enrichment workflows.
Must understand data integrity, idempotency, failure recovery, backpressure, and pipeline observability.
Experience with batch and real-time processing patterns.Production database expertise – Strong PostgreSQL (or equivalent) skills including schema design, query optimization, migrations, indexing strategies, and working with large datasets (1M+ records).
Understands when to use relational vs. document vs. vector storage.Async Python and concurrency – Strong understanding of asyncio, concurrent processing patterns, and event-driven architectures.
Must be comfortable with SQS/queue-based processing, background workers,



and managing concurrent API calls to external services.AI/ML Systems (Non-Negotiable)Production LLM integration – Must have built and shipped systems using OpenAI, Anthropic, or AWS Bedrock APIs.
Should be able to discuss prompt engineering, structured outputs, function calling/tool use, token optimization, and error handling patterns.Agentic AI and tool use – Experience building AI systems that make autonomous decisions, call external tools, and chain multi-step reasoning.
Familiarity with agent frameworks (LangGraph, CrewAI, OpenAI Agents SDK, or custom implementations).
Understanding of planning patterns, guardrails, and when to use agents vs. deterministic pipelines.AI evaluation and testing – Experience building evaluation frameworks for non-deterministic AI systems.
Should understand how to measure output quality systematically: golden datasets, LLM-as-judge patterns, regression testing, and behavioral monitoring in production.RAG and retrieval systems – Hands-on experience building retrieval-augmented generation pipelines.
Must understand chunking strategies, embedding models, hybrid retrieval (vector + keyword), reranking, and relevance evaluation.Vector database expertise – Production experience with at least one of PostgreSQL/PGVector, Weaviate, FAISS, Pinecone, or Qdrant.
Should be able to discuss indexing strategies, approximate nearest neighbor tradeoffs, and performance optimization.Infrastructure & DevOpsAWS cloud services – Working experience with core AWS services (ECS/Fargate, Lambda, RDS, S3, SQS, CloudWatch).
Should understand serverless patterns, container orchestration, and cloud cost management.Docker and containerization – Production deployment experience with container orchestration, health checks, and resource management.Observability and LLMOps – Experience with logging, monitoring, alerting, and debugging distributed systems in production.
For AI systems specifically: tracing agent runs, monitoring LLM call quality and latency, detecting behavioral drift, and debugging non-deterministic failures.Git workflows and CI/CD – Collaborative development with branching strategies, code reviews,



and automated deployment pipelines.Preferred QualificationsSoftware engineering foundation – Background in building APIs, web applications, or backend services.
Engineers who gained data pipeline and AI/ML skills because the product demanded it, rather than coming from a pure research or data science background, are strongly preferred.Third-party API integration experience – Track record of integrating complex external APIs (CRMs, enrichment services, telephony providers, payment systems).
Understands OAuth flows, webhook handling, rate limit management, and graceful degradation when third-party services fail.ATS/HR tech background – Experience with Bullhorn, Greenhouse, Workday, or similar platforms.
Understanding of candidate lifecycle, matching algorithms, and recruiting workflows.Voice AI systems – Experience with ElevenLabs, OpenAI Realtime API, WebRTC, SIP/telephony integration, or speech synthesis pipelines.MCP (Model Context Protocol) – Experience building or consuming MCP servers for agent tooling and context management.AI coding tools proficiency – Active use of Claude Code, Cursor, GitHub Copilot, or similar AI-assisted development tools in daily workflow.Guardrails and AI safety – Experience implementing input/output validation layers, PII/sensitive data filtering, prompt injection defense, and content safety checks for production AI systems.
Familiarity with tools like Guardrails AI or Nemo Guardrails.Multi-model architecture – Experience working with multiple LLM providers and understanding when to use which model for cost, latency, and quality tradeoffs.Knowledge graphs – Experience with Neo4j or similar graph databases for relationship-based data modeling and traversal.Cost optimization at scale – Track record of optimizing LLM token usage, caching strategies, and multi-provider routing to reduce AI infrastructure costs.Large-scale data processing – Experience processing 1M+ records with performance optimization, failure handling, and data quality validation at scale.About UsSTAND 8 focuses on the "bleeding edge" of technology and leverages automation, process, marketing, and over fifteen years of success and growth to provide a world-class experience for our customers, partners, and employees.
Our mission is to impact the world positively by creating success through PEOPLE, PROCESS, and TECHNOLOGY.Check out more at ; and reach out today to explore opportunities to grow together!
By applying to this position, your data will be processed in accordance with the STAND 8 Privacy Policy.
#J-*****-Ljbffr

Postúlate en Kit Empleo: kitempleo.com.mx/empleo/57ez1y

📌 Senior Ai Engineer / Data Engineer (Jalisco)
🏢 Stand8 Technology Consulting
📍 Jalisco