Senior AI Prompt Engineer (Python & GenAI)
Location: Gurgaon / Hyderabad, India
Work Type: [Hybrid / Onsite]
Years of experience: 6 to 9
About the Role
We are looking for a Senior AI Prompt Engineer with strong expertise in Python, database management, and Google Cloud Platform (GCP) to design, build, and scale production-grade AI-driven applications. In this role, you will bridge the gap between core backend architecture and modern Generative AI capabilities—optimizing LLM prompts, integrating APIs, and building resilient data pipelines.
Key Responsibilities
Backend Development & API Engineering: Design, build, and maintain scalable RESTful APIs and microservices using Python (FastAPI / Flask) and SQL databases.
LLM Integration & Prompt Engineering: Architect prompt templates, construct system workflows, and call LLM APIs (OpenAI, Anthropic, or Vertex AI / Gemini) for production use cases.
System Debugging & Optimization: Perform end-to-end debugging of complex backend pipelines, optimizing latency, cost, and reliability of LLM inference calls.
Cloud & Infrastructure: Deploy and manage services on GCP (e.g., Cloud Run, Cloud Functions, BigQuery, Vertex AI).
Data Management: Write optimized SQL queries, handle schema design, and manage data validation and ingestion logic.
Required Technical Skills
Python Expertise: 4+ years of hands-on experience in Python with strong asynchronous programming and advanced debugging skills.
Generative AI & LLMs: Proven experience with prompt engineering, API calls to LLM providers, and orchestration frameworks (e.g., LangChain, LlamaIndex, or native SDKs).
Database & SQL: Strong proficiency in relational databases (PostgreSQL, MySQL, or BigQuery) and writing/optimizing complex SQL queries.
Cloud Infrastructure: Hands-on experience with GCP services (e.g., Vertex AI, Cloud Run, Pub/Sub, Compute Engine) or equivalent cloud experience.
Software Engineering Practices: Solid understanding of Git, Docker, microservices architecture, and unit/integration testing.
Nice-to-Have Skills
Experience building RAG (Retrieval-Augmented Generation) pipelines or working with Vector Databases (Chroma, Pinecone, pgvector).
Exposure to multi-agent frameworks (e.g., LangGraph, AutoGen, CrewAI).
Knowledge of GCP MLOps or Vertex AI Pipelines.
New