Mandatory Skills Description:

- AWS Bedrock — hands-on: model access, Knowledge Bases, Lambda integration (primary AI platform)AI agents & Agentic tooling — practical knowledge of designing and operatin
- gAI agents, including agentic workflows, reusable skills, rules/guardrails, commands, and multi-tool/multi-agent orchestratio
- nRAG pipeline — end-to-end implementation: chunking,embedding, vector indexing, retrieval, generatio
- nPrompt engineering — zero-shot, few-shot, chain-of-thought, structured output (JSON mode), multi-turnVector databases — working knowledge of OpenSearch, Pinecone, or Faiss; understands vector vs. graph DBdifferenc
- eLLM guardrails — input/output filtering, hallucination mitigation strategiesFine-tuning vs. RAG — ability to reason through which approach fits a given proble
- mLLM orchestration — LangChain, LangGraph, or LlamaIndexEmbeddings — understands semantic similarity; experience with Amazon Titan Embed or equivalentPython — for Lambda functions, AI pipeline scripting, and data processin
- gJava — 3+ years of hands-on test automation developmentAppium / UiAutomator2 — mobile/Android UI automationAndroid / ADB — device management, test executionReportPortal or equivalent test reporting too
- lREST API — concepts and hands-on usageJenkins / CI-CD — pipeline debugging and integrationAWS — S3, Lambda, API Gateway, IAM, OpenSearch ServerlessDocker — containerized test execution environment

s Project Descrip tio

- n:We are building and maintaining one of the largest OTT platform test automation frameworks, serving millions of customers across streaming TV platforms. The team develops a Java/Appium-based automation framework for Android TV devices and is actively expanding it with AI-powered to
- oling.We are looking for a Senior AI Developer. This is a hybrid role combining the design and development of AI-powered internal tools with hands-on test automation engineering skills.



The idóneo candidate is a software engineer who understands both QA automation and modern LLM/RAG systems — and can translate test engineering problems into practical AI solution

s. Responsib iliti

- es:Design and implement AI-powered solutions fo
- cused on:Automated test failure triage — LLM + RAG pipeline classifying ReportPortal failures (logs, stack traces, screenshots) into structured categories (PRODUCT_BUG, AUTOMATION_BUG, SYSTEM_ISSUE) using AWS Bedroc
- k +ClaudeAI-based Change-Based Testing (CBT) — LLM-driven test case selection using semantic similarity between code changes and test
- coverageAI test case generation from feature specs, Jira tickets, and Confluence docu
- mentationBuild and maintain end-to-end RAG pipelines: document ingestion → chunking → embedding → OpenSearch Serverless vector store → retrieval → LLM response g
- enerationDevelop AWS Lambda functions (Python 3.12) and API Gateway REST endpoints to integrate AI capabilities into CI/CD
- pipelinesApply prompt engineering best practices (system prompts, structured JSON output, guardrails) and drive continuous evaluation of LLM solution
- accuracyUse Cursor IDE with MCP integrations, agentic workflows, and context/rules files to accelerate test code generation and ma
- intenanceWrite, maintain, and expand automated test suites in Java (Appium / UiAutomator2) for Android TV platformsDevelop and maintain functional, regression, NFR, and CBT testsui
- tesTriage and resolve test failures in ReportPortal; integrate AI triage results with QMetr
- y (QTM4J)Support CI/CD pipeline health — participate in Nightly Build, RC, and release automation runs via Jenk
- insContribute to framework codebase improvements — bug fixes, refactoring, enh
- ancementsParticipate in Kanban ceremonies and PI planning under the ART t
- eamPresent AI solution demos to stakeholders and engineering leadershipDocument AI system architecture, RAG pipelines, and tools in Conflue

nce

📌 Automators Mid AI Developer (México)
🏢 Luxoft
📍 México