Informacje o stanowisku

About your team

You’ll join AI Engines – the team building the backend “brain” of AI Agents in Text App.

AI Agents are intelligent, task-performing assistants powered by our Text Intelligence platform. They understand context, communicate naturally, and can take meaningful actions: from answering customer questions using the Knowledge Hub, to guiding human agents, collecting data, or automating tasks in third-party systems. In chats, they appear as chatbots; in tools like Copilot they power smart suggestions and actions.

Our team makes this possible by designing scalable backend systems that will be able to handle millions of conversations daily , building APIs and services for agent management, developing the reasoning layer that drives agent decisions, and continuously improving knowledge retrieval and agent skills.

You will be responsible for:

• Building and maintaining the core backend architecture (Vector Database, AI Engines, Knowledge Hub, etc.).

• Designing and optimizing scalable systems capable of handling very high traffic and real-time data flows especially for high-volume chat and data ingestion.

• Migrating implementations from legacy systems to a modern ecosystem.

• Collaborating with AI researchers to experiment, validate, and deploy new AI features into production.

• Conducting R&D and experiments with AI Agents ecosystems, including prompt management and reasoning approaches.

• Designing and extending RESTful APIs and service integrations for AI and data-heavy use cases.

• AI Agent integrations with MCP servers, shaping how agents connect and operate across systems.

• Participating in code reviews, architecture discussions, and technical decision-making, aligning backend engineering with the overall AI strategy.

You may be a good fit for this role if you:

• Have 6+ years of experience in backend development, building scalable and efficient systems.

• Work fluently with Node.js and TypeScript, including queues, streams, and async programming.

• Have hands-on experience with real-time communication (WebSockets, async service-to-service messaging).

• Have experience in commercial work on artificial intelligence project and understand AI and LLM integration, especially concepts like RAG, agentic systems, semantic search, and vector databases.

• Understand SQL databases (e.g., Postgres) and know how to design, optimize, and maintain them in data-intensive environments.

• Bring experience with NoSQL databases, especially Elasticsearch

• Know how to run and scale services on Google Cloud Platform and Kubernetes, including serverless computing and data pipelines.

• Enjoy solving complex technical challenges in microservices, high-traffic systems, concurrency, and performance optimization.

Bonus if you also:

• Worked on SaaS products or AI-driven platforms.

• Have experience with workflow automation or low-code/no-code tools.

Our Tech stack:

(You don’t need to tick every box — we value curiosity, versatility, and a growth mindset more than deep mastery of a single stack.)

• Core backend & languages: Node.js, TypeScript, Fastify

• Databases & data handling: PostgreSQL, Redis, ElasticSearch

• Scalability & communication: PubSub, Webhooks, SSE

• AI-related: LLMs, LangGraph

• Infrastructure & deployment: Docker, GitHub Actions, Prometheus, Grafana

• Testing & reliability: Vitest, Supertest, Playwright

How we work

We’re a hybrid team – remote when it makes sense, onsite when it matters most.

Once per quarter, your whole team spends 5 working days together at our Wrocław office – a time for focused execution, unblocking work, and driving key outcomes.

Our office is open year-round – drop by anytime.

Wrocław - Oferty pracy w okolicznych lokalizacjach