Python/GenAI Engineer (Hybrid: NYC or NJ)

As a Python/GenAI Engineer, you will design, build, and deploy intelligent, production-grade applications that apply generative AI to real-world challenges for financial services clients. In this client-facing technical role, you will develop LLM-powered solutions, build scalable Python services and data pipelines, and integrate AI capabilities into enterprise workflows. You will partner closely with data scientists, software engineers, business analysts, and client stakeholders to deliver AI solutions that meet strict enterprise standards for accuracy, governance, scalability, and security.

Essential Functions & Key Responsibilities

GenAI Application Development: Design, develop, and deploy LLM-powered applications such as intelligent assistants, document summarization, and workflow automation, using frameworks like LangChain or LlamaIndex and models from providers such as OpenAI, Anthropic, or Azure OpenAI.

Retrieval-Augmented Generation (RAG): Architect and implement RAG pipelines using vector databases (e.g., Pinecone, FAISS, pgvector), embedding models, and chunking strategies to ground model outputs in enterprise data.

Prompt Engineering & Evaluation: Craft, test, and iterate on prompts and agentic workflows, and establish evaluation frameworks to measure accuracy, relevance, hallucination rates, and latency.

Python Backend & API Development: Build scalable Python services and RESTful APIs using FastAPI or Flask, with clean, well-tested, and maintainable code.

Data Engineering & Pipelines: Develop data ingestion and transformation pipelines using Pandas, SQL, and cloud-based data services to prepare structured and unstructured data for AI workloads.

Cloud Deployment & MLOps: Deploy and monitor AI solutions on cloud platforms (AWS, Azure, or GCP) using Docker, CI/CD pipelines, and observability tooling to ensure reliability and cost efficiency.