Senior Fullstack Data Scientist – GenAI / LLM / RAG

Senovo IT is looking for an experienced Senior Fullstack Data Scientist to join an enterprise GenAI programme focused on building production-ready solutions using LLMs, RAG, AI Agents and modern Generative AI frameworks.

Location: Poland – 100% Remote Contract: B2B Language: English only

The Role

You will work across the full GenAI development lifecycle — from discovery and architecture through hands-on development and production deployment. The role combines Data Science, Python engineering and GenAI solution design, with a strong focus on RAG, LLM applications and AI agents.

Key Responsibilities

• Design and deliver end-to-end Generative AI solutions based on LLMs, RAG and AI Agents.
• Translate business requirements into scalable GenAI architectures.
• Build RAG pipelines using vector databases, hybrid search, reranking and query transformation.
• Develop GenAI applications using LangChain, LangGraph, LlamaIndex or similar frameworks.
• Build production-grade backend/API components in Python.
• Work with prompt engineering, model selection and fine-tuning including LoRA, QLoRA and SFT.
• Implement LLM evaluation, validators, guardrails, PII controls and human-in-the-loop workflows.
• Design and integrate MCP servers/clients for agent-based applications.
• Integrate GenAI solutions with enterprise applications and cloud platforms.
• Support technical estimations and architectural decisions.
• Mentor Data Scientists and Engineers and contribute to reusable GenAI components and best practices.

What We're Looking For

• 6+ years of experience in Data Science / AI Engineering.
• 4+ years of production-grade Python development within AI/ML projects.
• 2+ years of commercial experience building production LLM / GenAI solutions.
• Strong hands-on experience with RAG, LLMs, chatbots and AI Agents.
• Experience with LangChain, LangGraph, LlamaIndex or similar GenAI frameworks.
• Hands-on knowledge of MCP servers/clients.
• Strong understanding of LLM evaluation, validators and guardrails.
• Experience with vector databases, retrieval techniques and semantic/hybrid search.
• Strong Python development skills including testing, packaging and production deployment.
• Experience with Azure preferred, although AWS or GCP experience is also relevant.
• Familiarity with CI/CD, Docker and containerised deployments.
• Strong English communication skills.

Nice to Have

Experience with Spark, Databricks, Kubernetes, GitHub Actions, GitLab, Azure DevOps, multimodal models, multi-agent orchestration or other advanced Agentic AI frameworks.