Senior Artificial Intelligence Specialist
⚲ Warszawa
Do uzgodnienia
Wymagania
- AI
- Python
- RAG
- GenAI
Opis stanowiska
Why this role exists:
We are growing our AI team and are looking for a Senior AI / Generative AI Engineer to build and operate production-grade LLM-based systems across the platform.
This role focuses on applied Generative AI: internal AI automation, chatbots, AI assistants, and MCP-based services already used in production. You will work on top of an existing ML and data platform, building systems that are reliable, maintainable, and practical to operate.
This is a hands-on engineering role with end-to-end ownership. Not research. Not prompt-only.
What you’ll drive:
Technical Ownership
• Own LLM-based systems from design to production support.
• Design architectures for Generative AI systems (RAG, agents, tool/context serving).
• Make clear trade-offs between quality, latency, cost, and complexity.
• Set engineering standards for building and operating AI systems in production.
• Act as a technical reference point for applied GenAI.
Hands-on AI Engineering
• Build and maintain production LLM-powered systems.
• Develop chatbots and AI assistants with predictable behavior.
• Design and implement RAG pipelines (ingestion, embeddings, retrieval, generation).
• Implement agent-style workflows with tool/function calling.
• Build and integrate MCP servers or similar context/tool-serving components.
• Integrate AI systems with backend services and ML infrastructure.
Production & Reliability
• Design evaluation frameworks for LLM outputs.
• Monitor LLM behavior, system health, and costs in production.
• Address performance, scalability, and operational issues.
• Handle production incidents and contribute to long-term fixes.
• Design systems with failure modes, fallbacks, and graceful degradation.
What makes you a GR8 fit
Must-have
• Strong software engineering background.
• Proven experience building LLM-based systems in production.
• Hands-on experience with: LLMs and RAG architectures, Chatbots or conversational AI systems, Tool/function calling and agent-style patterns.
• Experience with context or tool-serving systems (MCP or similar).
• Experience integrating AI into real-time production products.
• Understanding of performance, scalability, and cost trade-offs.
• Cloud experience (preferably AWS).
• Strong engineering fundamentals (testing, debugging, reviews, observability).
Nice-to-have
• Multi-agent or workflow-based systems.
• Fine-tuning or adapting open-source LLMs.
• ML platforms / MLOps background.
• Experience operating latency- or cost-sensitive systems.
• Production incident ownership in AI systems.
Tech Stack:
•
Languages: Python, SQL.
• LLMs: Amazon Bedrock, OpenAI, Anthropic, open-source models.
• Frameworks: LangChain, LangGraph, Pydantic, Langfuse.
• RAG: Embeddings, Qdrant / FAISS / OpenSearch / pgvector.
• Cloud: AWS (ECS / EKS / Lambda, S3, OpenSearch).
• DevOps: Docker, Git, CI/CD.
Why you’ll love working here:
Benefits Cafeteria — annual budget you allocate to:
Sports • Medical • Mental health • Home office • Languages.
Work-life & support
• Paid maternity/paternity leave + monthly childcare allowance.
• 20+ vacation days, unlimited sick leave, emergency time off.
• Remote-first + tech support + coworking compensation.
• Team events (online/offline/offsite).
• Learning culture with internal courses + growth programs.
Our culture & core values:
GR8 Tech culture is how we win — through trust, ownership, and a growth mindset. We move fast, stay curious, and keep it real, with open feedback, room to experiment, and a team that’s got your back.
FUELLED BY TRUST: we’re open, honest, and have each other’s backs.
OWN YOUR GAME: we take initiative and own what we do.
ACCELER8: we move fast, focus smart, and keep it simple.
CHALLENGE ACCEPTED: we grow through challenges and stay curious.
BULLETPROOF: we’re resilient, ready, and always have a plan.
We are growing our AI team and are looking for a Senior AI / Generative AI Engineer to build and operate production-grade LLM-based systems across the platform.
This role focuses on applied Generative AI: internal AI automation, chatbots, AI assistants, and MCP-based services already used in production. You will work on top of an existing ML and data platform, building systems that are reliable, maintainable, and practical to operate.
This is a hands-on engineering role with end-to-end ownership. Not research. Not prompt-only.
What you’ll drive:
Technical Ownership
• Own LLM-based systems from design to production support.
• Design architectures for Generative AI systems (RAG, agents, tool/context serving).
• Make clear trade-offs between quality, latency, cost, and complexity.
• Set engineering standards for building and operating AI systems in production.
• Act as a technical reference point for applied GenAI.
Hands-on AI Engineering
• Build and maintain production LLM-powered systems.
• Develop chatbots and AI assistants with predictable behavior.
• Design and implement RAG pipelines (ingestion, embeddings, retrieval, generation).
• Implement agent-style workflows with tool/function calling.
• Build and integrate MCP servers or similar context/tool-serving components.
• Integrate AI systems with backend services and ML infrastructure.
Production & Reliability
• Design evaluation frameworks for LLM outputs.
• Monitor LLM behavior, system health, and costs in production.
• Address performance, scalability, and operational issues.
• Handle production incidents and contribute to long-term fixes.
• Design systems with failure modes, fallbacks, and graceful degradation.
What makes you a GR8 fit
Must-have
• Strong software engineering background.
• Proven experience building LLM-based systems in production.
• Hands-on experience with: LLMs and RAG architectures, Chatbots or conversational AI systems, Tool/function calling and agent-style patterns.
• Experience with context or tool-serving systems (MCP or similar).
• Experience integrating AI into real-time production products.
• Understanding of performance, scalability, and cost trade-offs.
• Cloud experience (preferably AWS).
• Strong engineering fundamentals (testing, debugging, reviews, observability).
Nice-to-have
• Multi-agent or workflow-based systems.
• Fine-tuning or adapting open-source LLMs.
• ML platforms / MLOps background.
• Experience operating latency- or cost-sensitive systems.
• Production incident ownership in AI systems.
Tech Stack:
•
Languages: Python, SQL.
• LLMs: Amazon Bedrock, OpenAI, Anthropic, open-source models.
• Frameworks: LangChain, LangGraph, Pydantic, Langfuse.
• RAG: Embeddings, Qdrant / FAISS / OpenSearch / pgvector.
• Cloud: AWS (ECS / EKS / Lambda, S3, OpenSearch).
• DevOps: Docker, Git, CI/CD.
Why you’ll love working here:
Benefits Cafeteria — annual budget you allocate to:
Sports • Medical • Mental health • Home office • Languages.
Work-life & support
• Paid maternity/paternity leave + monthly childcare allowance.
• 20+ vacation days, unlimited sick leave, emergency time off.
• Remote-first + tech support + coworking compensation.
• Team events (online/offline/offsite).
• Learning culture with internal courses + growth programs.
Our culture & core values:
GR8 Tech culture is how we win — through trust, ownership, and a growth mindset. We move fast, stay curious, and keep it real, with open feedback, room to experiment, and a team that’s got your back.
FUELLED BY TRUST: we’re open, honest, and have each other’s backs.
OWN YOUR GAME: we take initiative and own what we do.
ACCELER8: we move fast, focus smart, and keep it simple.
CHALLENGE ACCEPTED: we grow through challenges and stay curious.
BULLETPROOF: we’re resilient, ready, and always have a plan.
🔍 Dekoder Ogłoszenia
🟡
This is a hands-on engineering role with end-to-end ownership. Not research. Not prompt-only.
Oczekuje się, że będziesz tworzyć i wdrażać rozwiązania od początku do końca, a nie tylko eksperymentować z promptami czy prowadzić badania teoretyczne.
🔴
Own LLM-based systems from design to production support.
Będziesz odpowiedzialny za cały cykl życia systemu, od koncepcji po utrzymanie w środowisku produkcyjnym, co może oznaczać długie godziny pracy.
🟡
Make clear trade-offs between quality, latency, cost, and complexity.
Będziesz musiał podejmować trudne decyzje, które mogą wpływać na jakość lub wydajność systemu w zamian za inne korzyści.
🟡
Set engineering standards for building and operating AI systems in production.
Oczekuje się, że będziesz tworzyć i egzekwować najlepsze praktyki, co może oznaczać konieczność przekonywania innych do swoich rozwiązań.
🔴
Develop chatbots and AI assistants with predictable behavior.
Osiągnięcie w pełni przewidywalnego zachowania modeli językowych w złożonych zastosowaniach jest wyzwaniem, które może wymagać znacznych nakładów pracy.