Senior GenAI Data Scientist - Lead LLM/RAG Apps (Remote)

Lingaro; Town of Poland (NY); Hybrid; USD 140,000 - 180,000; Full time

Benefits offered by this job

Remote-friendly

Office option

Udemy learning platform

Flexible hours

Job summary

Lingaro in the United States seeks a Senior Data Scientist focused on GenAI to lead design and deployment of LLM-powered solutions, including retrieval augmented generation and agents. You will mentor teams and shape architecture across data ingestion, retrieval, orchestration, and UI layers.

The role requires hands-on Python production code, experience with LangChain/LlamaIndex, cloud environments, and strong communication to non-technical stakeholders. Remote-friendly; flexible hours.

Qualifications

• 6+ years in Data Science/AI engineering.
• 4+ years production-ready Python AI code development.
• 2+ years production-ready LLM-related code development (RAG).
• Strong experience with GenAI frameworks and evaluation.

Responsibilities

• Lead discovery and design for GenAI use cases (LLM decisions, RAGs, agents, guardrails).
• Build end-to-end GenAI apps: data ingestion, retrieval layer, orchestration, API/backend, and UI.
• Design and implement RAG pipelines with vector databases and hybrid search.
• Perform model selection, prompting, fine-tuning, and A/B testing.
• Implement safety, governance, and PII controls.
• Collaborate with data engineers, product owners, and full-stack developers.
• Mentor data scientists/engineers in GenAI patterns and best practices.

Skills

GenAI

LLMs

Python production code

LangChain

LlamaIndex

LangGraph

Cloud platforms (Azure/GCP/AWS)

CI/CD

Tools

LangChain

LlamaIndex

LangGraph

LangGraph

Job description

Lingaro in the United States seeks a Senior Data Scientist focused on GenAI to lead design and deployment of LLM-powered solutions, including retrieval augmented generation and agents. You will mentor teams and shape architecture across data ingestion, retrieval, orchestration, and UI layers.

The role requires hands-on Python production code, experience with LangChain/LlamaIndex, cloud environments, and strong communication to non-technical stakeholders. Remote-friendly; flexible hours.