Senior AI Engineer: Agentic Workflows & LLMs

Proxify

Ciudad de Mendoza

Hybrid

ARS 200,803,000 - 262,589,000

Full time

2 days ago

Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Professional growth

Competitive USD-based pay

Exciting projects

Flextime: remote and office options

Job summary

AgileEngine is seeking aSenior AI Engineer to design and build agentic workflows and AI-powered products for enterprise customers in higher education. You will lead development of AI agents, tool-using LLM applications, and orchestrated workflows across teams.

Ideal candidates have 5+ years in software product development, deep Java/Spring Boot experience, and strong AWS, TypeScript, and Python skills. Join a people-first culture delivering production-grade AI solutions.

Qualifications

5+ years in a software product development environment.
Strong proficiency with Java and Spring Boot.
Experience with relational databases.
Hands-on experience building AI agents or tool-using LLM apps.
Experience using agents to support coding, testing, release management, or incident response.
Senior-level experience building and operating production software systems.
Experience with TypeScript, Python, RESTful APIs, and AWS infrastructure.
Experience with APIs, workflow engines, event-driven architectures, integrations, or distributed systems.
Strong understanding of testing, observability, security, permissions, and failure recovery.
Ability to turn ambiguous opportunities into practical, reliable technical solutions.
Strong communication skills and ability to influence engineering practices across a team.
Experience building enterprise SaaS or multi-tenant systems.
Leadership mindset and ability to drive changes across teams.

Responsibilities

Design and build agentic workflows that coordinate tools, services, data, and human approvals.
Develop reusable patterns for agent orchestration, tool use, context management, memory, and multi-agent collaboration.
Use agentic coding tools throughout the development lifecycle, including planning, implementation, testing, debugging, refactoring, code review, and documentation.
Integrate agents into software development, testing, deployment, support, and operational workflows.
Establish standards for agent evaluation, observability, reliability, security, and governance.
Prototype new agentic capabilities and turn successful experiments into production systems.
Build complete, usable products—not just demonstrations or isolated model integrations.
Identify opportunities to improve engineering productivity and product delivery through agentic development.
Mentor engineers and help shape an agentic-first technical strategy across the organization.
Collaborate with product and engineering leaders to connect agentic capabilities to meaningful outcomes.
Demonstrate the ability to use AI coding agents as productive engineering collaborators across an application codebase.
Provide agents with clear context, constraints, architecture, acceptance criteria, and technical direction.
Review, test, secure, and improve agent-generated code rather than accepting outputs without verification.
Decompose complex application work into agent-ready tasks while maintaining architectural consistency and product intent.
Create workflows in which agents can reason, select tools, call APIs, manage state, recover from failures, and escalate to people when appropriate.
Design agentic applications around real user needs, including intuitive experiences, reliable workflows, permissions, audit trails, and meaningful error handling.
Move from prototype to production by addressing performance, scalability, security, monitoring, evaluation, cost, and ongoing maintenance.
Understand problems deeply, make appropriate tradeoffs, and deliver complete solutions that customers can depend on.