AI Data Scientist- RAG, SLM & Distributed Data...

We are looking for a mid-level AI Engineer with hands-on experience in Retrieval-Augmented Generation (RAG)systems, Small Language Models (SLMs), and distributed databases such as Google Cloud Spanner.

You will work closely with senior engineers and product teams to build scalable AI systems that integrate retrieval pipelines, language models, and distributed transactional infrastructure. This role is ideal for someone who has already built AI features in production and wants to deepen their expertise in applied GenAI systems.

AI RAG pipelines, Embeddings, Prompt engineering

Models SLM/LLM integration

Database Spanner schema design, SQL optimization

Backend Python, APIs

Cloud GCP, * 3-5 years of software engineering experience.

• 1-2 years working with LLM or RAG-based systems.

• Strong proficiency in Python.

• Experience with:

o Embedding models and vector search

o LangChain, LlamaIndex, or similar frameworks

o API development (FastAPI/Flask)

• Experience working with Google Cloud Spanner or similar distributed SQL databases.

• Solid understanding of distributed systems fundamentals.

• Comfortable working in cloud environments (GCP preferred). * Experience fine-tuning or quantizing small language models.

• Familiarity with evaluation metrics for retrieval systems (Recall@K, etc.).

• Knowledge of:

o Vertex AI

o Pub/Sub

o Dataflow

• Experience optimizing AI inference for cost and latency.

• Exposure to CI/CD pipelines.