Senior AI & Data Engineer
Description Bolsterup is transforming the construction industry with AI-powered intelligence. We’re looking for an AI Engineer passionate about building agentic workflows, LLM-driven solutions, and smart automation. This role suits someone with experience at the intersection of AI, data engineering, and automation, ideally from AI SaaS, data-heavy platforms, or applied AI startups. What you’ll do: - Build AI agents with OpenAI, Gemini, and LangChain. - Create data pipelines for structured & unstructured data (web scraping, PDFs, Excel). - Implement OCR, vector search (Pinecone), and RAG systems. - Automate workflows using n8n & Python. What we need: ✅ Expert in Python and AI integrations. ✅ Skilled in web scraping, OCR, embeddings, vector DBs. ✅ Experience with custom model training & agent orchestration. If you love building AI-driven products, designing intelligent workflows, and working with cutting-edge tech, we want to talk to you! Requirements Key ResponsibilitiesAI & LLM Development • Build agentic workflows using LangChain, OpenAI, Gemini, and custom orchestration. • Design context-aware RAG systems for accurate retrieval and response. • Fine-tune models for domain-specific tasks using LoRA, PEFT, RLHF. Data Processing & Extraction • Build robust web scrapers for structured and unstructured sources. • Implement OCR solutions for extracting data from PDFs, images, and scanned documents. • Parse Excel sheets, PDFs, and semi-structured data, extracting and matching entities across datasets. • Normalize and structure raw scraped and document data for downstream AI workflows. Vectorization & Retrieval Systems • Implement and optimize data vectorization pipelines for semantic search. • Use Pinecone, FAISS, or Weaviate for vector storage and similarity search. • Apply dimension reduction techniques (PCA, UMAP) for efficiency. Workflow Orchestration & Automation • Use n8n and similar tools for rapid prototyping and automation. • Build modular pipelines for continuous data ingestion and transformation. Infrastructure & Integrations • Develop APIs and connectors to integrate AI-driven insights with Bolsterup’s core platform. • Deploy solutions using Docker, serverless architectures, and cloud platforms (GCP/AWS). • Implement monitoring for AI pipelines, including token usage and latency tracking. Required Skills & Experience • Python Expert – Advanced proficiency in async programming, data processing (pandas, NumPy), and automation. • Web Scraping Expertise – Experience with Playwright, Puppeteer, Scrapy, and anti-bot evasion techniques. • Document Parsing & OCR – Skilled in Tesseract, AWS Textract, Google Document AI, or similar. • LLM Development – Hands-on with OpenAI, Gemini, LangChain, and building custom agents. • Vector Database Knowledge – Experience with Pinecone, FAISS, and embedding optimization. • Data Structuring & Entity Matching – Experience with data normalization, deduplication, and fuzzy matching. • Workflow Automation – Proficient in n8n, Zapier, or other orchestration platforms. • Cloud & Deployment – Familiar with Docker, serverless functions, and GCP/AWS. Nice-to-Have Skills • Experience with Vertex AI and AI model deployment on cloud. • Familiarity with multi-modal AI (text, image, tabular). • Knowledge of data governance and privacy best practices. • Prior experience with Stream Chat, Cloudflare Workers, and CDN-based deployments. • Experience building backend services with either Django or NestJS Benefits • Opportunity to build the future of AI in Contech. • Fully remote role • Competitive compensation and equity. • Employee stock options • Cutting-edge AI infrastructure and a fast-paced, innovation-driven culture. Apply tot his job