AI Algorithm Engineer

Growatt New Energy B.V.
Capelle aan den IJssel, Netherlands
17 days ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Languages
English, Chinese

Job location

Capelle aan den IJssel, Netherlands

Tech stack

Artificial Intelligence
Data analysis
Information Engineering
Data Visualization
Elasticsearch
Information Retrieval
Python
Knowledge-Based Systems
Neo4j
NumPy
Rapid Prototyping Process
Data Processing
Feature Engineering
Large Language Models
Grafana
FastAPI
Pandas
Matplotlib
Scikit Learn
Plotly
GPT
Data Pipelines
Docker
Microservices

Job description

Growatt is building an AI-powered after-sales support system to automate customer support queries with full traceability and confidence-gated responses. We are looking for an Intelligent Data Analysis Engineer who combines energy-sector domain knowledge with AI-augmented data engineering skills to design, build, and optimize the data and ML pipelines that power this system. You will work across a microservice architecture spanning document ingestion, semantic search, knowledge graph extraction, and LLM-based answer generation., * Data Pipeline Development - Build and maintain Python-based ingestion pipelines that process technical manuals, troubleshooting guides, and product documentation into searchable knowledge stores

  • Embedding & Retrieval Optimization - Develop and tune the embedding service and retrieval gateway using vector search and BM25 fusion to maximize recall and precision for solar inverter support queries
  • Knowledge Graph Construction - Design extraction schemas to build a product knowledge graph capturing device relationships, fault patterns, and resolution procedures with full provenance tracking
  • Quality & Observability - Define evaluation metrics, build feedback loops, and curate test datasets, monitor confidence-gate thresholds (Answer/Ask/Decline/Handoff) and continuously improve automation rates
  • AI-Assisted Rapid Prototyping - Use LLM-assisted coding workflows (Claude) to rapidly prototype data processing scripts, analysis tools, and service components, accelerating development cycles across the platform
  • Domain-Informed Feature Engineering - Leverage solar energy and power electronics domain expertise to design features, taxonomies, and retrieval strategies that improve the system's ability to resolve technical support queries accurately
  • Cross-Service Integration - Collaborate with the AI and OSS teams to ensure retrieved evidence meets citation and confidence requirements

Requirements

Do you have experience in Technical support?, Do you have a Master's degree?, * MSc or PhD in Materials Science, Physics, Electrical Engineering, Data Science, or a related STEM field

  • Strong Python skills (Pandas, NumPy, Scikit-learn) with experience building data processing and analysis pipelines
  • Experience with AI/ML workflows - embeddings, vector similarity search, or information retrieval systems
  • Domain knowledge in renewable energy, solar PV systems, battery technology, or power electronics
  • Proven AI-assisted development - productive use of LLM coding assistants (Claude, ChatGPT, Copilot) for rapid prototyping and data analysis
  • Data visualization proficiency (Matplotlib, Plotly, or Grafana dashboards) for communicating insights to technical and non-technical stakeholders
  • Scientific rigor - experience with statistical analysis, and evidence-based decision making

Nice to Have

  • Experience with Elasticsearch, Neo4j, or graph-based knowledge systems
  • Familiarity with FastAPI, Docker, and microservice architectures
  • Experience with LangChain/LangGraph or LLM orchestration frameworks
  • Background in NLP, document processing, or semantic search
  • Proficiency in Chinese (Mandarin) for collaboration with Growatt's global R&D teams

Apply for this position