GenAI Engineer: Python, LLM Apps & RAG | Hybrid NJ/NY

Braintrust; United States; Hybrid; USD 80,000 - 113,000; Full time

Job summary

Braintrust is seeking a Python/GenAI Engineer in a hybrid role based in New York/New Jersey. You will design, build, and deploy LLM-powered applications for financial services, collaborating with data scientists, engineers, and client stakeholders to ensure accuracy, governance, and scalable solutions.

Responsibilities include building Python services, implementing RAG pipelines, and deploying AI workloads on cloud platforms with Docker and CI/CD. Strong emphasis on security and compliance.

Qualifications

• Design, build, and deploy GenAI-powered applications for financial services clients.
• Develop LLM-powered solutions and scalable Python services.
• Implement RAG pipelines grounding outputs in enterprise data.

Responsibilities

• Develop GenAI applications using LangChain or LlamaIndex.
• Architect RAG pipelines with vector databases and embeddings.
• Craft prompts, evaluate models, and optimize latency and accuracy.
• Build Python backends and RESTful APIs with FastAPI or Flask.
• Create data pipelines using Pandas and SQL for AI workloads.
• Deploy AI solutions on AWS/Azure/GCP with CI/CD and observability.
• Ensure governance, security, and compliance in AI systems.

Skills

GenAI

RAG

Prompt engineering

Python

Pandas

Cloud/MLOps

Security

Agile

Tools

LangChain

LlamaIndex

OpenAI

Azure OpenAI

Pinecone

FAISS

Docker

FastAPI

Job description

Braintrust is seeking a Python/GenAI Engineer in a hybrid role based in New York/New Jersey. You will design, build, and deploy LLM-powered applications for financial services, collaborating with data scientists, engineers, and client stakeholders to ensure accuracy, governance, and scalable solutions.

Responsibilities include building Python services, implementing RAG pipelines, and deploying AI workloads on cloud platforms with Docker and CI/CD. Strong emphasis on security and compliance.