Senior Production Ml Engineer & Ai Platform Lead (Remote Latam)

Ryz Labs; Quilmes; Hybrid; ARS 185,448,000 - 278,173,000; Full time

Benefits offered by this job

Flexible remote/work office options

USD-based pay with comprehensive perks

Job summary

AgileEngine, a leading software partner for Fortune 500 brands, seeks an AI Platform Context Lead to architect the knowledge graph and context layer for an enterprise AI ecosystem. You will oversee semantic retrieval, RAG, and agent integrations across Slack, Google Workspace, and AI assistants, driving quality, governance, and scalable patterns.

You will collaborate with SMEs to design, test, and maintain AI agents and workflows, ensuring secure, compliant, and production-ready capabilities

Qualifications

• 6+ years of development experience with hands-on Tech Lead work.
• Designed or owned an enterprise context/retrieval architecture and knowledge graph.
• Built production AI agents, skills, or integrations using RAG and related frameworks.
• Ability to identify correct vs wrong retrieval and prioritize fixes by business impact.
• Experience with enterprise SaaS platforms (Slack, Google Workspace, Glean, Claude, ChatGPT).
• Strong systems administration including IAM, config, monitoring, and incident response.
• Experience collaborating across multiple business functions with minimal supervision.
• Excellent troubleshooting, technical writing, and stakeholder communication.

Responsibilities

• Design and continuously improve the context and knowledge graph grounding search and agent responses.
• Review agent outputs to catch missing or wrong context and backlog fixes by priority.
• Maintain cross-team visibility to fix systemic context gaps architecturally.
• Partner with SMEs to design, build, test, and maintain AI agents, prompts, and workflows.
• Decide whether a need is best solved by a skill, workflow, connector, or knowledge-graph grounding.
• Translate platform strategy into technical designs and production-ready plans.
• Ensure implementations are scalable, secure, and align with standards.
• Build connectors, APIs, and RAG/semantic-search patterns with source permissions.
• Create discovery tooling and question sets for autonomous scoping.
• Enable functional groups to curate context with tooling and guidance.
• Establish testing and evaluation practices for agent output quality, reliability, and safety.
• Configure and maintain Slack, Google Workspace/Gemini, Glean, and other assistants.
• Apply access-management, monitoring, and change-control best practices.
• Implement data handling controls in partnership with security and privacy teams.
• Flag elevated connectors early and route them for security review.
• Maintain technical docs, runbooks, and vendor coordination.
• Maintain incident response and service-continuity procedures.
• Drive continuous improvement in platform reliability, search quality, and cost efficiency.

Job description

AgileEngine is an Inc. 5000 company that creates award-winning software for Fortune 500 brands and trailblazing startups across 17+ industries. We rank among the leaders in areas like application development and AI/ML, and our people-first culture has earned us multiple Best Place to Work awards.

WHY JOIN US

If you're looking for a place to grow, make an impact, and work with people who care, we'd love to meet you!

ABOUT THE ROLE

We are looking for an AI Platform Context Lead to build the context and knowledge layer behind an enterprise AI ecosystem. The role combines knowledge-graph design, semantic retrieval, RAG, and agent integrations across Slack, Google Workspace, Glean, and AI assistants. You will improve answer quality through evaluation, governance, and reusable self-service patterns.

MUST HAVES

• 6+ years of experience in development roles, with hands-on experience as a Tech Lead.
• Has designed and/or owned a knowledge graph or enterprise context/retrieval architecture end to end, not merely queried one that someone else built.
• Demonstrated experience building production-quality AI agents, skills, or integrations using MCP, function calling, RAG, and enterprise search.
• Can distinguish "wrong retrieval" from "right retrieval, missing context" in an eval trace, and prioritize fixes by business impact.
• Hands-on experience administering or engineering enterprise SaaS, search, or AI platforms (e.g., Slack, Google Workspace, Glean, Claude, ChatGPT).
• Strong systems-administration background, including identity/access management, configuration, monitoring, and incident response.
• Experience working across multiple business functions, with the ability to turn "what should we ask before we start" into a checklist others can use unsupervised.
• Strong troubleshooting, technical writing, and stakeholder-communication skills, with the ability to lead through influence without direct authority.

WHAT YOU WILL DO

• Design, curate, and continuously improve the company context and knowledge graph that grounds search and agent responses, managing schema, coverage, freshness, and retrieval quality as an ongoing responsibility rather than a one-time build, with a stated accuracy and efficiency baseline that improves over time.
• Review agent and skill outputs to catch cases where a result missed user intent because the underlying context was missing or wrong, and turn those findings into a prioritized backlog of fixes so that intent-breaking context gaps are resolved rather than left to resurface.
• Maintain enough cross-team visibility that a systemic context gap gets fixed once, architecturally, instead of being patched repeatedly.
• Partner with subject-matter experts to design, build, test, and maintain AI agents, skills, prompts, and workflows using MCP, function calling, and comparable frameworks.
• Decide whether a need is best solved by a skill, workflow, connector, or knowledge-graph grounding, based on where the logic belongs rather than what is fastest to ship.
• Translate platform strategy into technical designs, integrations, and implementation plans, and turn pilots into reliable, production-ready capabilities by evaluating platform capabilities.
• Ensure implementations are scalable, secure, and aligned with organizational standards.
• Build and maintain connectors, APIs, and RAG/semantic-search patterns while preserving source-system permissions.
• Build and maintain the discovery tooling and question sets other teams use to scope new AI use cases on their own, reducing the hands-on involvement required from this role.
• Enable functional groups to curate and maintain their own context in the way that works best for them through tooling, patterns, and guidance, rather than one-size-fits-all mandates.
• Establish testing and evaluation practices for agent output quality, reliability, and safety.
• Configure, administer, and maintain Slack, Google Workspace/Gemini, Glean, and other AI assistants.
• Apply access-management, monitoring, and change-control best practices, and troubleshoot complex platform issues.
• Implement technical controls for access, data retention, and sensitive-data handling in partnership with security, privacy, and compliance teams.
• Flag connectors needing elevated or write access early, during design, and route them to security for review.
• Maintain technical documentation, runbooks, and vendor coordination.
• Maintain incident-response and service-continuity procedures.
• Drive continuous improvement in platform reliability, search quality, and cost efficiency over time.

PERKS AND BENEFITS

• Professional growth : Mentorship, TechTalks, and personalized growth roadmaps.
• Competitive compensation : USD-based pay with education, fitness, and team activity budgets.
• Exciting projects : Modern solutions with Fortune 500 and top product companies.
• Flextime : Flexible schedule with remote and office options.