Applied AI Engineer
ITEAMLY SPÓŁKA Z OGRANICZONĄ ODPOWIEDZIALNOŚCIĄ
⚲ Kraków
30 000–39 000 zł netto (+ VAT) / mies.
Wymagania
- Python
- LangChain
- OpenAI API
- RAG
- AI
- TypeScript
- Agentic AI
Opis stanowiska
Nasze wymagania:
Commercial experience building and shipping production LLM applications
Experience designing and implementing AI evaluation frameworks
Practical experience with LLM-as-a-Judge, golden datasets, or regression testing approaches
Experience building agentic AI workflows and tool-using agents
Strong software engineering fundamentals and backend development experience
Experience with Python and/or TypeScript
Experience designing APIs and scalable backend services
Knowledge of prompt engineering and prompt lifecycle management
Understanding of defensive engineering patterns such as rate limiting, idempotency, and backoff strategies
Mile widziane:
Experience with LangChain or similar orchestration frameworks
Experience with Retrieval-Augmented Generation (RAG)
Experience with vector databases and semantic search
Experience with Vision-Language Models (VLMs)
Experience building multimodal AI systems
Experience creating automated evaluation dashboards and monitoring solutions
O projekcie:
We are looking for an Applied AI Engineer to build production-grade LLM and VLM-powered features, owning the AI logic and backend systems from concept to production.
Zakres obowiązków:
Design, develop, and deploy AI-powered product features using LLMs and multimodal models
Build and maintain backend services supporting AI applications and workflows
Develop evaluation frameworks, golden datasets, and automated quality measurement pipelines
Design and implement multi-step agent workflows with tool usage, memory, error recovery, and human-in-the-loop processes
Build scalable APIs and backend components supporting AI services
Improve model reliability, performance, and response quality in production environments
Implement engineering best practices including testing, monitoring, rate limiting, retry mechanisms, and fault tolerance
Collaborate with cross-functional teams to deliver end-to-end AI solutions
Oferujemy:
100% remote work.
Opportunity to work on production AI systems used by real users
Private healthcare
Multisport
Life insurance
High ownership and end-to-end responsibility for delivered solutions
Exposure to modern LLM, multimodal, and agent-based architectures
Ability to influence product direction and technical decisions
Collaboration with experienced engineers building AI-driven products
Commercial experience building and shipping production LLM applications
Experience designing and implementing AI evaluation frameworks
Practical experience with LLM-as-a-Judge, golden datasets, or regression testing approaches
Experience building agentic AI workflows and tool-using agents
Strong software engineering fundamentals and backend development experience
Experience with Python and/or TypeScript
Experience designing APIs and scalable backend services
Knowledge of prompt engineering and prompt lifecycle management
Understanding of defensive engineering patterns such as rate limiting, idempotency, and backoff strategies
Mile widziane:
Experience with LangChain or similar orchestration frameworks
Experience with Retrieval-Augmented Generation (RAG)
Experience with vector databases and semantic search
Experience with Vision-Language Models (VLMs)
Experience building multimodal AI systems
Experience creating automated evaluation dashboards and monitoring solutions
O projekcie:
We are looking for an Applied AI Engineer to build production-grade LLM and VLM-powered features, owning the AI logic and backend systems from concept to production.
Zakres obowiązków:
Design, develop, and deploy AI-powered product features using LLMs and multimodal models
Build and maintain backend services supporting AI applications and workflows
Develop evaluation frameworks, golden datasets, and automated quality measurement pipelines
Design and implement multi-step agent workflows with tool usage, memory, error recovery, and human-in-the-loop processes
Build scalable APIs and backend components supporting AI services
Improve model reliability, performance, and response quality in production environments
Implement engineering best practices including testing, monitoring, rate limiting, retry mechanisms, and fault tolerance
Collaborate with cross-functional teams to deliver end-to-end AI solutions
Oferujemy:
100% remote work.
Opportunity to work on production AI systems used by real users
Private healthcare
Multisport
Life insurance
High ownership and end-to-end responsibility for delivered solutions
Exposure to modern LLM, multimodal, and agent-based architectures
Ability to influence product direction and technical decisions
Collaboration with experienced engineers building AI-driven products
🔍 Dekoder Ogłoszenia
🔴
owning the AI logic and backend systems from concept to production
Oznacza to pełną odpowiedzialność za cały cykl życia funkcji AI, od pomysłu po wdrożenie i utrzymanie, co może wiązać się z dużą presją i szerokim zakresem obowiązków.
🟡
Strong software engineering fundamentals and backend development experience
Chociaż brzmi to jak standardowe wymaganie, w kontekście AI może oznaczać, że oprócz wiedzy o modelach, oczekuje się solidnych umiejętności tworzenia skalowalnych i niezawodnych systemów backendowych, które będą obsługiwać te modele.
🟡
designing APIs and scalable backend services
Wskazuje na potrzebę budowania infrastruktury, która będzie w stanie obsłużyć duży ruch i złożone interakcje z modelami AI, co może wymagać zaawansowanych umiejętności architektonicznych.
🟢
build production-grade LLM and VLM-powered features
Podkreśla, że celem są gotowe do użycia funkcje, a nie eksperymenty, co oznacza, że oczekuje się wysokiej jakości kodu i stabilności rozwiązań.
🟡
multi-step agent work
Może oznaczać tworzenie złożonych, sekwencyjnych procesów, w których agenci AI wykonują wiele zadań, co wymaga dobrego zrozumienia logiki przepływu i zarządzania stanem.