AI Software Engineer

About Creatio

Creatio is an AI CRM and workflow platform where people and AI agents work together — with no limits on users, agents, or scale. We help midsize and large organizations run customer workflows in the AI era. With a global team and a large ecosystem of partners, Creatio serves thousands of customers in over 100 countries and automates tens of millions of workflows daily. Genuine care for our clients and partners is at the heart of our DNA. We’re proud to be recognized by top industry analysts as a Leader and Strong Performer in multiple Gartner and Forrester reports. In 2025, Creatio was named to Inc.’s Best Workplaces list, recognizing our commitment to employee wellbeing and a strong workplace culture.

The Role

We are looking for an AI Software Engineer to design, build, evaluate, and operate AI-powered capabilities within the Creatio platform. You will join the AI teams building the agent platform that enables AI agents to safely perform real work in the product: call tools and APIs, read and write data, maintain context, follow permissions, and escalate to humans when needed. The team also owns the core infrastructure for testing, monitoring, logging, observability, and cost/performance control, ensuring AI agents are reliable, scalable, secure, and production-ready. This role combines strong software engineering expertise with hands-on AI engineering experience. You will work on enterprise-grade AI solutions, including assistants, copilots, knowledge systems, semantic search, RAG-based capabilities, and agentic workflows.

Responsibilities

• Design and implement AI-powered product features within the Creatio platform: assistants, copilots, agentic workflows, knowledge systems, RAG, and semantic search.
• Design agent architectures - tools, memory and context strategy, orchestration, permissions, guardrails, and human-in-the-loop escalation - and choose the right pattern for each problem (single LLM call vs. tool-using agent vs. multi-agent).
• Engineer prompts, system instructions, and agent context as first-class artifacts: versioned, reviewed, and covered by evaluations.
• Integrate LLM providers, MCP servers and tools, enterprise data sources, embedding pipelines, and vector/hybrid search into the platform.
• Build evaluation datasets, offline and online evals, quality gates, and observability (tracing, logging, drift detection) for AI capabilities.
• Monitor and improve the quality, latency, cost, reliability, and security of AI capabilities in production, including prompt and model updates.
• Identify and mitigate AI-specific risks: prompt injection, data exfiltration through tools, hallucinations, over-permissioned agents, and sensitive-data leakage.
• Develop and maintain backend services using C# and .NET.
• Use AI coding assistants and engineering agents as the default development workflow; critically review and verify agent output; contribute reusable rules, skills, and prompts to the team.
• Follow the AI landscape closely and bring new models, tools, and patterns to the team.

What to expect from us

• Growth & Development: Clear career paths, mentorship opportunities, and access to continuous learning to help you reach your full potential.
• Flexibility & Well-Being: We provide flexible work arrangements and initiatives that empower you to manage your schedule effectively, stay productive, and thrive both personally and professionally.
• Recognition & Impact: A culture that celebrates achievements, values your ideas, and empowers you to make real contributions from day one.
• Innovative Culture: Be part of a company that embraces new ideas, modern technologies, and bold thinking to stay ahead of the curve.
• Benefits & Rewards Package: We provide competitive compensation and benefits designed to support you and your family. Our rewards approach goes beyond salary, recognizing your contributions and commitment. The exact package may vary depending on your country of residence and employment type.

Must have:

• Hands-on experience shipping LLM-based features to production: prompt engineering, function/tool calling, structured outputs, context-window and cost management.
• Practical understanding of agent architectures (tool loops, planner/executor, multi-agent, human-in-the-loop), MCP, and at least one agent framework or SDK.
• Working knowledge of RAG: chunking, embeddings, vector and hybrid search, re-ranking, grounding and citations, and common failure modes.
• Experience with AI evaluation (datasets, offline evals, LLM-as-judge), LLM observability and tracing, and AI security (prompt injection, OWASP Top 10 for LLM Applications, Responsible AI practices).
• Daily proficiency with AI coding agents: the ability to direct, review, and verify agent output rather than only write code by hand.
• Solid experience with C# and .NET, API design, distributed systems, and software architecture.
• Experience with SQL databases, automated testing, CI/CD, and cloud-native development; Docker and basic Kubernetes.
• Strong knowledge of engineering best practices and production-grade software development.

Nice to have:

• Python for prototyping, data work, and evaluation scripting.
• Hands-on experience with a major AI platform (Anthropic API, Azure OpenAI, AWS Bedrock, Google Vertex AI).
• Experience building agent-facing tools or MCP servers.
• LLMOps practices: prompt and model versioning, evaluation gates in CI/CD, canary rollouts of prompt changes.
• Fine-tuning, distillation, or adapter-based model customization.
• Experience with Creatio or other low-code CRM platforms.