Staff AI Product Engineer

Jobgether; Colombia; Remote; COP 657,722,000 - 986,582,000; Full time

Benefits offered by this job

Remote work across continents

Stock options

Paid time off and holidays

Comprehensive insurance

Job summary

Jobgether is seeking a Staff AI Product Engineer in Colombia to lead the architecture and development of a production-grade multi-agent system. You will own MCP integrations, data infrastructure, and evaluation frameworks, shaping the AI roadmap and engineering standards across the org.

The role requires 7+ years in full-stack development, strong leadership, and hands-on experience with AI tooling and enterprise systems. Remote, global teams, and a fast-moving startup environment are offered.

Qualifications

• 7+ years of full-stack software development experience, preferably B2B SaaS.
• Hands-on experience designing and deploying production-grade multi-agent systems.
• Experience building MCP servers or integrations used in production.
• Strong production engineering knowledge: reliability, observability, security, permissions.
• Ability to balance product thinking with technical leadership.
• Proficiency in React, TypeScript, Node.js, PostgreSQL, GraphQL, and LangGraph.
• Experience in an early-stage startup with small teams and ownership.
• Fluent with Claude Code or similar AI tools and building custom agents.
• Ability to design AI evaluation processes and safe AI actions.

Responsibilities

• Lead architecture and development of production-grade multi-agent systems across core tools.
• Own MCP integration development connecting internal systems with AI environments.
• Design centralized data infrastructure for AI agents and external tools.
• Build contextual memory and customer profiling for intelligent experiences.
• Establish reliability, observability, and secure execution for real customer data.
• Develop evaluation frameworks and automated tests based on real use cases.
• Define standards and best practices for agentic systems across engineering teams.
• Stay updated on AI models, orchestration tools, and emerging tech.
• Prototype new AI capabilities and present technical opportunities.

Skills

React

TypeScript

Node.js

PostgreSQL

GraphQL

LangGraph

Multi-agent systems

MCP integrations

Production engineering

AI fluency

Tools

MCP integrations

Job description

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Staff AI Product Engineer based in Colombia.

We are looking for an experienced AI Product Engineer to shape and lead the development of a next-generation AI product ecosystem for business operations. In this hands-on, high-impact role, you will own the architecture and technical direction of production-grade agentic systems, from multi-agent orchestration and Model Context Protocol (MCP) integrations to contextual memory and evaluation frameworks. You will transform complex business data into intelligent, actionable experiences that help companies automate workflows and make better decisions. Working closely with engineering leadership, product teams, and customers, you will influence the technical roadmap and establish engineering standards across the organization. This is an opportunity to work at the forefront of enterprise AI in a fast-moving, profitable startup environment that values experimentation, technical ownership, and practical innovation. You will have the autonomy to explore emerging technologies, challenge existing approaches, and bring ambitious AI products into production.

Accountabilities

• Lead the architecture, design, and development of a production-grade multi-agent system capable of safely executing actions across core business tools, including ERP, CRM, spreadsheets, calendars, email, analytics, and compliance platforms.
• Own the development and continuous improvement of Model Context Protocol (MCP) integrations that connect internal business systems with external AI environments and assistants.
• Design and implement a unified data infrastructure that consolidates information from multiple sources into a centralized layer accessible to AI agents and external tools.
• Build contextual memory and customer profiling systems that ingest business data and enable increasingly personalized, intelligent AI experiences.
• Establish robust reliability, observability, permission management, and durable execution mechanisms to ensure agents operate safely on real customer data.
• Develop and maintain comprehensive evaluation frameworks and automated tests based on real-world customer use cases to measure agent performance and prevent regressions.
• Define architectural standards, engineering patterns, and best practices for building, testing, deploying, and maintaining agentic systems across the engineering organization.
• Stay ahead of developments in AI models, agentic frameworks, orchestration tools, and emerging technologies, incorporating valuable innovations into the product architecture.
• Rapidly prototype new AI capabilities and present technical concepts and product opportunities to internal teams and customers.
• Work hands-on with AI-assisted development tools such as Claude Code, continuously improving personal engineering workflows and sharing effective practices with the wider team.
• Collaborate closely with engineering leadership, product teams, and customers to shape the AI roadmap, prioritize initiatives, and translate business challenges into impactful technical solutions.
• Provide technical mentorship and influence engineering direction while maintaining a strong focus on execution, product quality, and measurable customer outcomes.

Requirements:

• At least 7 years of full-stack software development experience, ideally building and scaling B2B SaaS applications.
• Proven, hands-on experience designing and deploying production-grade multi-agent systems, beyond experimental prototypes or personal projects.
• Demonstrated experience building and maintaining MCP servers or integrations used in production environments.
• Strong understanding of production engineering principles, including system reliability, observability, security, permissions, and safe workflow execution.
• Experience combining product thinking with technical leadership, including defining scope, making architectural decisions, and influencing product roadmaps rather than focusing exclusively on implementation.
• Proficiency in React, TypeScript, Node.js, PostgreSQL, GraphQL, and LangGraph, with the ability to quickly learn and adopt new technologies and frameworks.
• Previous experience in an early-stage startup environment, preferably within an engineering team of fewer than 20 people, with a track record of taking ownership and setting direction in ambiguous situations.
• Strong practical AI fluency, including daily use of Claude Code or comparable AI development tools, and the ability to build custom agents, skills, and automated workflows.
• Ability to design and implement effective AI evaluation processes, understand when to use language models versus conventional code, and build appropriate safeguards around AI-generated actions.
• Experience deploying AI agents to real users with suitable guardrails, monitoring, observability, and rollback mechanisms.
• Strong product and engineering judgment, with the ability to distinguish high-value opportunities from unnecessary complexity and deliver intuitive AI-powered experiences.
• Excellent communication skills, with the confidence to raise concerns, propose solutions proactively, and communicate complex technical concepts clearly.
• Collaborative, low-ego mindset, prioritizing team success, product quality, and shipped outcomes over internal politics or individual recognition.
• Additional advantages include experience with supply chain software, ERP, CRM, B2B marketplaces, or accounting platforms; UX design capabilities; advanced agentic systems, evaluation frameworks, or agent-to-agent protocols; independent product development using AI coding tools; and familiarity with the cannabis industry.

Benefits:

• Competitive annual salary: $200,000-$300,000, depending on experience, skills, and qualifications.
• Fully remote working opportunities across four continents.
• Employee-friendly stock option terms, including a 10-year exercise window after departure once two years of service have been completed.
• 18 days of paid time off annually, plus 11 public holidays.
• Separate sick leave that does not count toward annual paid time off.
• Medical, dental, and vision insurance, as well as a 401(k) plan for eligible US employees.
• Access to leading AI models, development platforms, and tools, alongside a generous AI stipend for additional resources.
• Opportunities to participate in company-wide AI workshops, training sessions, demonstrations, and hackathons.
• Annual in-person team offsites to encourage collaboration and strengthen team connections.
• A collaborative, innovation-driven environment that encourages experimentation, technical ownership, and continuous learning.
• Direct exposure to customers and opportunities to influence product strategy and engineering decisions.
• Benefits and employment arrangements may vary depending on country of residence and employment type.

How Jobgether works:

We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role’s core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team.

We appreciate your interest and wish you the best!

Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.