Key Responsibilities

Design and develop LLM‑powered agents and intelligent workflows to solve complex business problems.
Build and optimize Retrieval‑Augmented Generation (RAG) pipelines using embeddings and vector databases.
Engineer high‑quality prompts, including few‑shot learning, structured outputs, and tool/function calling.
Implement text‑to‑SQL and automated insight generation pipelines for analytics use cases.
Design and maintain evaluation frameworks to measure model accuracy, latency, reliability, and cost.
Collaborate closely with backend and platform teams to productionize, scale, and monitor AI systems.
Continuously experiment, debug, and improve model behavior through structured testing and iteration.

Required Skills

Strong hands‑on experience in Python.
Practical experience working with LLM APIs (e.g., OpenAI, Anthropic).
Experience with LLM orchestration frameworks such as LangChain, LlamaIndex, or similar.
Solid understanding of embeddings, semantic search, vector databases, and RAG architectures.
Strong debugging, experimentation, and problem‑solving mindset in applied AI systems.

Preferred / Good‑to‑Have Skills

Experience with MLOps / LLMOps tooling such as MLflow, Langfuse, Weights & Biases (W&B).
Exposure to multi‑agent systems and agent coordination patterns.
Domain experience in analytics, data platforms, or pharma/life sciences.
Knowledge of cost optimization techniques, model selection, and routing strategies across multiple LLMs.

Notice Period : Immediate to 30 Days

Location : PAN India

Data Scientist