Software Engineer, Agent Development

ActiveCampaign is seeking a Software Engineer to join our Kraków Hub and build production-ready AI agents for autonomous marketing. Our platform empowers businesses to automate their customer engagement — and we are now extending that with intelligent, agentic workflows that can reason, act, and adapt on behalf of our customers. Our first wave of agents is already in production. This role will drive the expansion, building the next generation of autonomous experiences across the full breadth of the platform.

You 'll work at the intersection of solid software engineering and applied AI — designing, building, evaluating, and operating agents that run at scale in a production marketing automation platform. This means engineering rigor comes first: agents need to be reliable, observable, performant, and safe before they are clever.

Our Kraków Hub houses multiple engineering teams — Forms, Integrations, Ecommerce, Agency, CRM, Mobile, CampaignsUI, and Content — working across different product pillars with a shared focus on building agentic workflows into all core functionalities across the platform. You will collaborate closely with these teams, understanding their domains and building agents that integrate seamlessly into the broader system,

This is not a pure research or ML role. We need engineers who can build — end to end — from prompt design through backend orchestration to frontend integration, and who can ship, measure, and iterate fast. Our environment moves quickly — we value high ownership, tight feedback loops, and close cross-functional collaboration. If you thrive in a hands-on, high-pace setting where you build, ship, and iterate rapidly, this role is for you.




What your day could consist of:

Designing and building production-grade AI agents and autonomous marketing workflows across the ActiveCampaign platform

Implementing multi-step agentic flows involving LLM orchestration, tool use, and integration with platform services

Working with LLM APIs (prompt engineering, response handling, evaluation) and building reliable, testable agent pipelines

Designing and running agent evaluations — building eval frameworks, defining quality metrics, and continuously measuring agent accuracy, reliability, and performance in production at scale

Monitoring and optimizing agent performance — latency, cost, token usage, error rates — and iterating rapidly based on production dataIterating on agent behavior based on user feedback, observability data, and quality metrics

Leveraging AI-assisted development tools and practices in your daily workflow — you don't just build AI features, you build with AI

Writing production-quality code in Python for agent services and backend orchestration

Contributing to PHP backend and frontend (React/Ember) integration points where agents interact with the core platform

Building and maintaining APIs, data flows, and service interfaces that agents depend on

Working iteratively — shipping code fast, learning from production, and improving continuously

Ensuring code quality through testing, code review, and adherence to engineering standards

Participating in on-call rotation for incidents related to agent services

Working closely with Product, Design, and domain engineering teams to define agent capabilities and user experiences

Engaging in pairing and code reviews across teams

Contributing to documentation of agent architectures, patterns, and best practices

Maintaining regular overlap with US-based teams (Chicago timezone) to ensure alignment and tight collaboration across the organization

What we're looking for:

2-4 years of experience in a software engineering role

Hands-on experience building and running AI agents or agentic workflows in a production environment — not just prototypes or side projects

Experience with agent evaluation and performance optimization — you know how to measure whether an agent is working well and how to make it better

Solid backend development skills in Python; working familiarity with PHP is a plus

Understanding of how to build reliable, testable, and observable systems

Active practitioner of AI-driven development — you use AI coding assistants and agentic development tools as part of how you work, not just what you build

Ability to work iteratively and ship code fast — you're comfortable with rapid release cycles and learning from production

Familiarity with DB technologies: MySQL, DynamoDB, Redis

Strong problem-solving skills and ability to work across multiple codebases and technologies

Fluent in English (B2 minimum)

Willingness to work flexible hours with regular afternoon availability to overlap with US Central timezone

Experience with agentic AI frameworks or multi-agent orchestration patterns

Familiarity with Model Context Protocol (MCP) or tool-use patterns for LLM agents

Experience building eval pipelines or quality measurement systems for LLM-based features

Frontend experience with React or EmberFamiliarity with AWS, CI/CD practices, and observability tooling

Understanding of prompt engineering, evaluation methodologies, or LLM fine-tuningExperience in SaaS, marketing automation, or CRM domain

What we offer:

A front-row seat in ActiveCampaign's AI-first transformation — you'll build the autonomous marketing agents customers interact with

Collaboration with experienced engineers across the Kraków Hub, including senior and staff-level technical leadership

An environment that values ownership, fast iteration, and learning by doing

Active investment in AI-first engineering practices and tooling

Hybrid work model from our Kraków office with flexibility to adjust working hours for collaboration with US-based teams (Chicago timezone overlap)