Senior GenAI Engineer / LLM Developer
Cluj-Napoca, Romania (Remote)
Cluj-Napoca, Romania (Remote)
About Nexttech
Founded in 2015, Nexttech has built a solid foundation in delivering comprehensive IT solutions tailored to meet diverse client needs. With expertise spanning five key industry sectors—Banking, Energy, Telecom, Automotive and E-commerce & Logistics—we provide nearshore and onshore services designed to drive efficiency and support strategic growth.
Our team supports every phase of the Software Development Life Cycle (SDLC), from developing detailed roadmaps and resolving complex software challenges to ensuring quick time-to-market and optimized ROI.
About the Role:
Enterprise Knowledge Base Chatbot – Production GenAI
We are looking for a Senior Developer to help build a production-grade, LLM-powered enterprise knowledge base chatbot.
This is a hands-on engineering role focused on delivering a real, working system — not a research experiment and not a demo.
You will work on implementing Retrieval-Augmented Generation (RAG), integrating enterprise data sources, building APIs, and ensuring the system runs reliably in production. While architectural thinking is important, this role is primarily about strong engineering execution.
You should be comfortable working in modern AI stacks, writing clean backend code, and collaborating in a multi-language environment.
Key Responsibilities:
• LLM Integration & Development:
Implement LLM-based chatbot functionality using frameworks such as LangChain and LangGraph.
• RAG Implementation:
Build and maintain document ingestion pipelines, embeddings, chunking logic, and vector search mechanisms.
• Backend Development (Python-first):
Develop backend services using Python (e.g., FastAPI), exposing APIs for chatbot interaction and system integration.
• Agent Workflows:
Implement structured LLM flows including prompt orchestration, tool calling, conversation memory, and response validation.
• Vector Database Integration:
Work with vector databases and hybrid search systems to enable efficient semantic retrieval.
• Enterprise Data Integration:
Connect to internal systems (APIs, document repositories, databases) and handle structured/unstructured data.
• Quality & Evaluation:
Improve prompt quality, reduce hallucinations, and implement evaluation mechanisms to ensure consistent responses.
• Containerized Deployment:
Package services using Docker and support CI/CD pipelines for deployment.
• Collaboration:
Work closely with product, infrastructure, and other developers to iteratively improve the system.
Must-Have Skills & Experience:
• Strong Python Skills (Mandatory):
Solid experience building backend systems with Python (FastAPI, async programming, API development).
• LLM & RAG Experience:
Hands-on experience with:
• Vector Databases:
Experience with at least one of:
• Data Processing:
Experience working with document ingestion, text chunking, metadata handling, and structured/unstructured data.
• API Development:
Strong understanding of REST APIs and system integration patterns.
• Containerization:
Experience with Docker.
• Clean Code & Testing:
Ability to write maintainable code with testing discipline and production mindset.
• Multi-Language Openness:
Willingness to work with Go or other languages if needed.
• Language Skills:
Fluent in English.
Nice to Have:
• Experience with Go
• Experience with:
What Makes This Role Attractive:
• Work on a real enterprise AI solution with immediate business impact
• Build production GenAI systems — not prototypes
• Modern AI stack (LangGraph, RAG, vector search)
• High ownership and strong technical autonomy
• Opportunity to grow into deeper AI or architecture responsibilities over time
