AI / LLM Engineer
DEVAPO SPÓŁKA Z OGRANICZONĄ ODPOWIEDZIALNOŚCIĄ
⚲ Warszawa, Ochota
Do uzgodnienia
Wymagania
- Python
- Docker
- AWS
- Microsoft Azure
- Google Cloud Platform
- LangChain
- LangGraph
- LlamaIndex
- Qdrant
- Weaviate
- Pinecone
- pgvector
- RAGAS
- LangSmith
- Arize
- Databricks
- Azure AI Foundry
- AWS Bedrock
Opis stanowiska
Nasze wymagania:
You've built something with LLMs that actually runs in production — doesn't matter if it was at a big company or a side project
Solid Python skills — not scripts, but clean code you're not ashamed of
Working knowledge of RAG: you understand why naive chunking fails and what to do about it
Experience with at least one agent framework (LangChain, LlamaIndex, LangGraph)
Familiarity with vector databases (Qdrant, Weaviate, Pinecone, pgvector — any)
You know how to ship: REST APIs, Docker, cloud basics (AWS / Azure / GCP)
English B2+ — client-facing role, calls and written communication included
Mile widziane:
Experience evaluating LLM outputs (RAGAS, LangSmith, Arize or similar)
MLflow or another experiment tracking tool
Databricks, Azure AI Foundry or AWS Bedrock
Fine-tuning experience (LoRA, PEFT, anything hands-on)
Kafka or streaming pipelines for real-time AI use cases
O projekcie:
We're looking for an engineer who genuinely gets excited about building things with AI — someone who shipped something real with LLMs, not just played with the API. You'll work on international projects for clients in banking, insurance, and telco (US, Netherlands, UK), translating messy business problems into working AI systems.
You don't need 10 years of "AI experience" — this field is too new for that. What matters is that you think clearly, learn fast, and can take an idea from whiteboard to production.
Zakres obowiązków:
Building LLM-powered applications and RAG systems for enterprise clients
Designing and implementing AI agents (LangChain, LangGraph, CrewAI or similar)
Integrating LLMs (OpenAI, Anthropic, Gemini, open-source) into existing systems
Building data ingestion pipelines: chunking, embedding, vector indexing
Writing production-grade Python code — APIs, tests, containers, the full stack
Working directly with clients: understanding their requirements, presenting solutions
Doing code reviews, writing docs, contributing to team engineering standards
Oferujemy:
Certifications and training funded
Private medical care (Medicover)
Multisport card
English language classes
Flexible working hours
Team meetups and integration events
Referral bonus
You've built something with LLMs that actually runs in production — doesn't matter if it was at a big company or a side project
Solid Python skills — not scripts, but clean code you're not ashamed of
Working knowledge of RAG: you understand why naive chunking fails and what to do about it
Experience with at least one agent framework (LangChain, LlamaIndex, LangGraph)
Familiarity with vector databases (Qdrant, Weaviate, Pinecone, pgvector — any)
You know how to ship: REST APIs, Docker, cloud basics (AWS / Azure / GCP)
English B2+ — client-facing role, calls and written communication included
Mile widziane:
Experience evaluating LLM outputs (RAGAS, LangSmith, Arize or similar)
MLflow or another experiment tracking tool
Databricks, Azure AI Foundry or AWS Bedrock
Fine-tuning experience (LoRA, PEFT, anything hands-on)
Kafka or streaming pipelines for real-time AI use cases
O projekcie:
We're looking for an engineer who genuinely gets excited about building things with AI — someone who shipped something real with LLMs, not just played with the API. You'll work on international projects for clients in banking, insurance, and telco (US, Netherlands, UK), translating messy business problems into working AI systems.
You don't need 10 years of "AI experience" — this field is too new for that. What matters is that you think clearly, learn fast, and can take an idea from whiteboard to production.
Zakres obowiązków:
Building LLM-powered applications and RAG systems for enterprise clients
Designing and implementing AI agents (LangChain, LangGraph, CrewAI or similar)
Integrating LLMs (OpenAI, Anthropic, Gemini, open-source) into existing systems
Building data ingestion pipelines: chunking, embedding, vector indexing
Writing production-grade Python code — APIs, tests, containers, the full stack
Working directly with clients: understanding their requirements, presenting solutions
Doing code reviews, writing docs, contributing to team engineering standards
Oferujemy:
Certifications and training funded
Private medical care (Medicover)
Multisport card
English language classes
Flexible working hours
Team meetups and integration events
Referral bonus
🔍 Dekoder Ogłoszenia
🔴
You've built something with LLMs that actually runs in production — doesn't matter if it was at a big company or a side project
Oczekiwane jest udokumentowane doświadczenie w wdrażaniu rozwiązań LLM, a nie tylko eksperymentowanie z API.
🟡
Solid Python skills — not scripts, but clean code you're not ashamed of
Szukają kogoś, kto pisze dobrze zorganizowany, testowalny kod, a nie tylko proste skrypty.
🟡
You know how to ship: REST APIs, Docker, cloud basics (AWS / Azure / GCP)
Oczekiwane jest praktyczne doświadczenie w deploymentcie aplikacji, a nie tylko teoretyczna wiedza.
🟢
You don't need 10 years of "AI experience" — this field is too new for that.
Nie szukają weteranów z dekadami doświadczenia, ale raczej osoby z aktualną, praktyczną wiedzą w szybko rozwijającej się dziedzinie.
🔴
translating messy business problems into working AI systems
Będziesz musiał radzić sobie z niejasnymi wymaganiami biznesowymi i przekładać je na konkretne rozwiązania AI.