Senior Data Scientist — AI for Pharma Insights (Remote)

Norstella; Baton Rouge (LA); Remote; USD 170,000 - 215,000; Full time

Benefits offered by this job

Medical and Prescription Drug Benefits

401k with Company Match

Paid Parental Leave

Open Vacation Policy & Holidays

Job summary

Norstella seeks a Senior Data Scientist to design and deploy production‑grade AI systems leveraging LLMs to solve pharma‑intelligence challenges. You will build multi‑agent workflows, RAG pipelines, and MCP‑driven data access while ensuring low‑latency APIs and robust testing.

You will mentor juniors, collaborate with product teams, and stay current with advances in NLP, AI, and distributed systems to drive impactful insights across the business.

Qualifications

• 5+ years of experience developing AI/ML applications and data driven solutions, preferably in regulated industries.
• Graduate degree in Computer Science, Engineering, Statistics or a related quantitative discipline, or equivalent work experience.
• Substantial depth and breadth in NLP, Deep Learning, Generative AI, LLMs, and other state of the art AI/ML techniques.
• Deep experience with LLM orchestration frameworks such as LangChain, LlamaIndex, or similar libraries.
• Expert‑level knowledge of LLM APIs (OpenAI, Anthropic Claude) and open‑source models (Llama, Mistral).
• Deep understanding of CS fundamentals, computational complexity and algorithm design.
• Experience with building large‑scale distributed systems in an agile environment and the ability to build quick prototypes.
• Excellent knowledge of Python and core data science and AI libraries including Pandas, NumPy, PyTorch, and similar.
• Experience building or utilizing Model Context Protocol (MCP) servers to bridge models with data tools.
• Strong background in scalable backend environments (Docker, Kubernetes, AWS/GCP).
• Experience moving AI from prototype to production‑grade services with monitoring, logging, and rate‑limiting.
• Ability to independently conduct research and develop appropriate algorithmic solutions to complex business problems.
• Experience mentoring junior team members.
• Excellent problem solving and communication skills.

Responsibilities

• Design and deploy production‑ready AI systems that leverage LLMs and advanced ML techniques to solve complex business problems across pharma intelligence.
• Build and maintain multi‑agent systems and agentic orchestration workflows using frameworks like LangChain, LangGraph, or AutoGen to execute autonomous tasks.
• Develop and optimize Retrieval‑Augmented Generation (RAG) pipelines, ensuring high‑fidelity context retrieval and vector database management.
• Implement and extend MCP (Model Context Protocol) servers to allow LLMs to interact safely and efficiently with local and remote data sources.
• Architect robust, scalable APIs and microservices to serve AI features to end‑users with low latency (FastAPI or similar).
• Collaborate with product partners and other scientists to identify new opportunities to apply AI / ML to our content and products.
• Conduct research and identify AI / ML algorithms and methods to solve specific business problems, and deliver these algorithms as microservices in collaboration with content and product engineering teams.
• Implement rigorous testing and evaluation frameworks for LLM outputs to ensure prompt stability, prevent regressions, and manage hallucination risks.
• Contribute towards the common data science platform.
• Stay up‑to‑date, constantly learning about advances in the field, and deliver periodic presentations to internal teams on these developments.
• All other duties as assigned

Skills

Python

Pandas

NumPy

PyTorch

LLMs

LangChain

LangGraph

AutoGen

RAG

MCP

FastAPI

Docker

Kubernetes

AWS/GCP

Vector DBs

LlamaIndex

Education

Graduate degree in CS/Engineering/Statistics

Tools

LangChain

LlamaIndex

OpenAI API

Anthropic Claude

Docker

Kubernetes

AWS

Job description

Norstella seeks a Senior Data Scientist to design and deploy production‑grade AI systems leveraging LLMs to solve pharma‑intelligence challenges. You will build multi‑agent workflows, RAG pipelines, and MCP‑driven data access while ensuring low‑latency APIs and robust testing.

You will mentor juniors, collaborate with product teams, and stay current with advances in NLP, AI, and distributed systems to drive impactful insights across the business.