AI Engineer [120-137 zł/h netto + VAT B2B]

Unit Application Development creates custom solutions for clients worldwide, focusing on generative AI solutions for enterprise-scale organizations. The team works on systems deployed in real business environments, including regulated sectors where data privacy, security, auditability, and model quality control are critical. Projects cover the entire process from defining needs and designing solutions with analysts, through development and client verification, to production deployment.

• Minimum 4 years of experience developing production solutions in Python
• Practical knowledge of FastAPI and asynchronous programming
• Experience with LLM and GenAI solutions, especially RAG, vector databases, retrievers, hybrid search, and prompt engineering
• Familiarity with LangChain or LlamaIndex
• Experience with Azure OpenAI, Amazon Bedrock, or OpenAI API
• Knowledge of PostgreSQL and pgvector or Qdrant
• Basic knowledge of Elasticsearch or OpenSearch
• Experience with Docker and basic Kubernetes or OpenShift
• Experience working with AWS or Azure
• Practice in CI/CD, unit and integration testing, Git, and code review
• Knowledge of Linux, basic networking, and security including OIDC/OAuth2, KMS/Secrets
• Experience with observability: logs, metrics, and tracing
• Skills in profiling and optimizing latency and AI solution costs
• Proficiency in Polish and English at a level enabling project work, minimum B2
• Awareness of data security and GDPR requirements in the context of GenAI

Nice to have:

• Knowledge of LangGraph, RAGFlow, Dify, n8n, or Temporal
• Experience with Ragas or Evals, prompt-CI, A/B testing
• Knowledge of OpenShift, Helm, Terraform, Keycloak
• Experience with RabbitMQ (gRPC, event-driven patterns)
• Knowledge of MLflow or W&B (basic fine-tuning, multimodal)
• TypeScript, Next.js, or Streamlit
• Elasticsearch or OpenSearch in production environments
• Experience in regulated sector projects
• Knowledge of ISO 42001, ISO 27001/27017, and basic SOC 2

• Design and implement GenAI applications, including RAG solutions
• Develop APIs and serving layers using FastAPI
• Build pipelines involving chunking, embeddings, indexing, hybrid search, and reranking
• Evaluate solution quality offline and online, prepare RAG regression tests, and monitor quality and costs
• Implement guardrails such as content filtering, prompt security, and access policies
• Integrate with client systems via REST, gRPC, ESB, or EventBus
• Monitor and ensure observability including logging, tracing, and metrics using OpenTelemetry
• Optimize performance, model usage costs, and latency
• Document technical decisions including ADRs and model cards
• Collaborate with frontend, backend, DevOps, business analysis, and project management teams
• Participate in client discussions for solution verification and project adjustments
• Support sales during presales stages

The company has implemented whistleblower protection procedures according to applicable law, ensuring safe reporting and full legal protection for candidates and employees.