onsite
AI/ML Engineer - Primotech
ML Engineer
Hands‑on AI Engineer building enterprise‑grade Generative AI services on Google Cloud, designing secure, scalable REST APIs and Retrieval‑Augmented Generation pipelines with LLMs, FastAPI, and BigQuery.
About the role
Key Responsibilities
- Design, develop, and maintain production‑ready REST APIs using Python and FastAPI.
- Build Retrieval‑Augmented Generation (RAG) pipelines leveraging Vertex AI Search and Gemini models.
- Integrate structured and unstructured data sources, optimizing queries and data flows with BigQuery.
- Orchestrate Large Language Model (LLM) calls, ensuring low latency, security, and scalability.
- Implement monitoring, logging, and automated testing to guarantee reliability in a cloud environment.
Requirements
- Minimum 2 years of professional experience developing backend services in Python.
- Proficiency with FastAPI and RESTful API design patterns.
- Hands‑on experience with Google Cloud services, especially Vertex AI, Gemini, and BigQuery.
- Understanding of Retrieval‑Augmented Generation concepts and LLM orchestration.
- Strong problem‑solving skills, ability to write clean, maintainable code, and work collaboratively in an agile team.