Data Scientist – RAG & Document Intelligence

170 - 200 PLN/ godz./ godz.B2BB2B (netto)

SeniorZdalnie·WarszawaFull-time·B2B

#462740·Dodano 4 dni temu·4

Źródło: justjoin.it

Aplikuj teraz

Tech Stack / Keywords

PythonRAGNLP LLMDataLakesAzure Apps

Podsumowanie oferty

You’ll design, experiment with, and implement a context-aware, multi-agent AI system that helps business users retrieve and act on knowledge in complex enterprise documents for an international Consumer Health company. You’ll shape retrieval strategies and model selection, using RAG, LLMs, and NLP to improve answer quality.

Wymagania

Strong Python skills and hands-on experience with machine learning and generative AI workflows, including production-grade code.
Solid NLP background, including text representation, semantic search, embeddings, and language model behaviour.
Deep hands-on experience designing and optimizing RAG pipelines over unstructured documents, including chunking strategies, embedding models, hybrid search, and re-ranking; examples include LightRAG, LlamaIndex, and LangChain.
Experience with document parsing and noisy, multimodal document formats, including extracting information from tables, charts, and figures.
Experience with LLM evaluation frameworks and RAG-specific quality metrics; examples include RAGAS, DeepEval, and Langfuse.
Familiarity with multi-agent AI frameworks such as LangGraph, LangChain, or Pydantic AI.
Experience with vector databases such as pgvector, Pinecone, Qdrant, or Weaviate.
Experience with Azure cloud services (Azure Apps, Containers, Storage, AI Search, AI Foundry) and/or AWS equivalents.
Experience with Databricks (Delta Lake, Unity Catalog, MLflow).
Strong analytical mindset and a structured, experiment-driven approach to problem solving.
Fluent written and spoken English.

Nice to have:

Hands-on experience with Databricks GenAI products: Vector Search, Agent Framework, Knowledge Assistance, Genie, or Agent Bricks.
API development and integration skills, such as FastAPI.
Knowledge of Model Context Protocol (MCP) for tool integration.
Understanding of knowledge management, taxonomy design, and metadata enrichment for enterprise document repositories.

Obowiązki

RAG pipeline optimization:

Test parsing and chunking strategies, embedding models, retrieval algorithms, re-ranking approaches, and context assembly techniques to improve answer quality and minimize hallucination.

Document intelligence:

Evaluate and benchmark document parsing solutions for PDFs, Word documents, presentations, scanned files, and mixed-format corpora.
Extract structured meaning from noisy inputs, including tables, charts, and figures.

Model evaluation:

Compare LLMs, embedding models, and retrieval models across accuracy, latency, reliability, and cost.
Build evaluation datasets and define RAG-specific quality metrics.

NLP and prompt engineering:

Work on semantic similarity, named entity recognition, query rewriting, and multi-turn conversation handling.
Craft, version, and systematically evaluate prompts and prompt chains.

Quality and cost:

Track token consumption, latency, and retrieval quality across experiments.
Make trade-offs between model capability and operational cost at enterprise scale.

Benefity

Budget for skills development and certifications as part of the collaboration.
Regular collaboration reviews and discussion of project scope.
Networking and team-building events for project teams.
Broad range of internal and international projects, with variety of clients and tasks.

Dofinansowanie szkoleń

Spotkania integracyjne

Craftware

17 aktywnych ofert

Zobacz wszystkie oferty

Aplikuj teraz