📝 Podrobnosti o nabídce práce
Required Qualifications & Experience
Backend Engineering
- Python (FastAPI) or Node.js; strong REST API design; Docker and containerization.
- Relational DB design (Postgres or equivalent); schema modeling, migrations, and query tuning.
NLP / AI
- Integrating LLMs (Azure OpenAI/OpenAI/Hugging Face, etc.).
- Chunking, embeddings, intent extraction; familiarity with vector databases.
Enterprise Practices
- Logging/monitoring, structured error handling; unit & integration testing.
- Git workflows; exposure to CI/CD; awareness of RBAC/security integrations.
Highly Desirable
- AI Planning & Decisioning: MDP, MCTS usage in agent workflows.
- Big Data: Apache Spark / Hadoop for large-scale processing.
- Streaming & Orchestration: Kafka, Airflow, or equivalents.
- Platform & Scale: Kubernetes for deployment/operations; cloud (Azure/AWS/GCP).
- Frameworks: LangChain/Haystack as accelerators where appropriate.
- UI for Demos: Basic React/Next.js for lightweight internal forms
In Digital Workplace, we are seeking a Backend Engineer with NLP specialization to join our User Support team’s agentic transformation. This role is critical to building the Agentic Content Management System (ACMS) — a modular, headless, AI-driven content management platform designed for ingesting, validating, structuring, and publishing enterprise knowledge.
Unlike a chatbot or single-channel solution, ACMS enables a system of agents that collaboratively create, enrich, and manage content, then deliver it across multiple channels — voice, mobile, chat, conversational interfaces, articles, and knowledge bases — serving users, human agents, and digital agents alike.
The engineer will start by delivering the Enhanced Article Co-Creation Agent, the first agent in a multi-agent system for complete knowledge article lifecycle management. It drafts first versions of knowledge content based on themes generated by the Signal Agent and performs four roles in one:
1. Writer — produces plain-language, user-centric articles.
2. Intent Structurer — breaks articles into machine-readable intents (e.g., goal, object, action).
3. Format Converter — structures output for AI and omnichannel use (JSON, Markdown, HTML).
4. Self-contained Module — optimized for agent consumption and reuse across platforms.
Beyond this initial project, the role will contribute to designing and scaling additional agentic microservices across the ACMS ecosystem
,[Microservices & APIs: Design, build, and operate production-grade microservices (FastAPI preferred or Node.js) with versioned REST contracts; uphold API-first, headless patterns for multi-channel delivery. , NLP/LLM Integration: Implement pipelines for text generation, intent/metadata extraction, chunking & embeddings; integrate vector search as needed (e.g., pgvector/Qdrant/Pinecone). , Data & Storage: Model and maintain Postgres schemas (articles, intents); manage migrations, performance, and data quality. , Packaging & Ops: Ship Dockerized services with configuration, observability (logging/metrics/tracing), runbooks, and basic SLOs; collaborate with the hub for Kubernetes deployments. , Security & Messaging: Implement OAuth2/OIDC, secure service-to-service communication, and leverage message brokers where appropriate. , Pipelines & Streaming: Contribute to real-time and batch ingestion (e.g., Kafka, Airflow) and/or cloud-native functions (AWS Lambda, Azure Functions, GCP Functions). , Agentic Planning: Where beneficial, apply AI planning/decision methods such as Markov Decision Processes (MDP) or Monte Carlo Tree Search (MCTS) to improve reliability and autonomy. , Collaboration: Partner with product owner, platform, data, and security teams on requirements, reviews, and releases aligned to enterprise standards. ] Requirements: Python, Docker, Azure, CI/CD, Apache Spark, Kafka, Airflow, Next.js Additionally: Private healthcare, Sport subscription, Canteen, Free parking, Modern office, In-house trainings.Kategorie
artificialIntelligence
-
Lokalita: Warszawa
-
Směnnost: fulltime - 40 hours per week
-
Nástup: IHNED
-
Firma: Bayer
-
❓ Vše, co o této práci potřebujete vědět
👉 Kde je tato práce?
Práce je v lokalitě Warszawa.
👉 Kdo na tuto pozici nabírá?
Tuto pracovní pozici nabízí firma Bayer.
👉 Jaká je směnnost?
Směnnost: fulltime - 40 hours per week.
👉 Kdy je nástup?
Nástup je od IHNED.