Overview
Software Engineer role focused on building and maintaining scalable AI-powered data ingestion, processing platforms, and AI/ML (including LLM) services.
What you'll do
- Design and develop web crawling, data ingestion, and AI-powered processing solutions using Python.
- Build scalable data pipelines to process HTML, PDF, and other structured/unstructured sources.
- Develop REST APIs for AI/ML services and data processing workflows.
- Implement AI/ML models or integrate LLMs for document parsing, classification, summarization, and information extraction.
- Design background processing, task scheduling, and distributed workloads.
- Build monitoring, logging, and observability for AI pipelines and backend services.
- Collaborate with Product, Data Science, DevOps, and Engineering teams to deliver production-ready solutions.
What you'll need
- 2-3 years of Python development experience with FastAPI, Django, or similar frameworks.
- Strong experience in AI/ML, Generative AI, or LLM application development.
- Experience with web scraping frameworks such as Scrapy or Playwright.
- Hands-on experience with NLP, document processing, or information extraction techniques.
- Experience integrating LLMs (OpenAI, Claude, Gemini, Llama, or similar) using LangChain or LlamaIndex.
- Knowledge of REST APIs, asynchronous programming, and distributed task processing (Celery, RabbitMQ, Kafka).
Nice to have
- Experience with RAG (Retrieval-Augmented Generation) architectures.
- Knowledge of vector databases such as Pinecone, Weaviate, Milvus, or pgvector.
- Experience with Hugging Face Transformers, PyTorch, or TensorFlow.
- Exposure to MLOps tools such as MLflow, Kubeflow, or model serving frameworks.
- Experience with Kubernetes and cloud-native deployments.
- Knowledge of OCR, computer vision, or multimodal AI models.
Details
- Focus on first 90 days objectives including understanding the AI platform by Day 30 and owning end-to-end delivery by Day 90.
Read the full description and apply on the company’s own careers page.
