GenAI & Python Engineer — LLM Apps for Enterprise

Braintrust; New York (NY); On-site; USD 140,000 - 210,000; Full time

Job summary

Braintrust seeks a Python/GenAI Engineer to design, build, and deploy production-grade GenAI applications for financial services clients. You will develop LLM-powered solutions, scalable Python services, and data pipelines, collaborating with data scientists, software engineers, and client stakeholders to ensure accuracy, governance, scalability, and security.

You will architect RAG pipelines, craft prompts, and evaluate model performance, latency, and reliability while delivering robust API

Qualifications

• Design, build, and deploy GenAI-powered applications for financial services clients.
• Develop LLM-based solutions with scalable Python services and data pipelines.
• Collaborate with data scientists, software engineers, and stakeholders to meet enterprise standards.

Responsibilities

• GenAI application development: create LLM-powered apps like assistants, summarization, and workflow automation.
• Implement Retrieval-Augmented Generation (RAG) pipelines with vector databases and embedding models.
• Craft and evaluate prompts and agentic workflows to measure accuracy and latency.
• Build scalable Python services and RESTful APIs with FastAPI or Flask.
• Develop data ingestion/transformation pipelines using Pandas, SQL, and cloud services.
• Deploy and monitor AI solutions on cloud platforms with Docker and CI/CD.

Skills

GenAI

Prompt engineering

API design

Data pipelines

Agile collaboration

Python development

Tools

LangChain

LlamaIndex

OpenAI

Anthropic

Azure OpenAI

Pinecone

FAISS

pgvector

FastAPI

Flask

Pandas

Docker

AWS

Azure

GCP

Job description

Braintrust seeks a Python/GenAI Engineer to design, build, and deploy production-grade GenAI applications for financial services clients. You will develop LLM-powered solutions, scalable Python services, and data pipelines, collaborating with data scientists, software engineers, and client stakeholders to ensure accuracy, governance, scalability, and security.

You will architect RAG pipelines, craft prompts, and evaluate model performance, latency, and reliability while delivering robust API