- Python & Async Frameworks: Solid proficiency in Python 3.x and async web frameworks like FastAPI or Celery to build high-throughput, multi-tenant background processing microservices.
- GenAI & LLM Orchestration: Familiarity with LLM APIs (Google Gemini/Vertex AI or OpenAI) and utilizing tools like Pydantic to enforce strict structured JSON outputs from unstructured data.
- Dynamic Prompt Engineering: Expertise in designing complex system instructions, few-shot prompting templates, and managing advanced model parameters like thinking budgets or temperature.
- Cloud Storage & Data Pipelines: Proficient in managing cloud data streams (Google Cloud Storage or S3) to ingest document assets (PDFs/Images)
and orchestrating async polling workflows with automated retry logic.
- ML Ingestion & Evaluation: Familiarity with ML preprocessing tools (Pandas, NumPy, OCR engines) and setting up statistical thresholds to evaluate extraction confidence scores and failure metrics.
(Note: Relevant applicants will receive an email requesting additional information as part of the next stage. The application process will be completed directly on the team's designated platform, and all subsequent communication and decisions regarding the opportunity are managed by the respective hiring team.)