Agentic AI Software Engineer

Provenir is the unified Decision Intelligence Platform that gives enterprises full control over end- to-end customer decisioning — to manage risk, drive growth, and transform business outcomes. By consolidating data, AI models, intelligence, agents and governance into a single decisioning environment, Provenir empowers business teams to configure and evolve strategy directly, while maintaining enterprise-grade reliability and regulatory compliance. Trusted by 120+ institutions in 60+ countries, Provenir processes over 4 billion decisions annually — turning architectural coherence into sustained risk performance and measurable value. Ready to solve meaningful challenges, work with enterprise customers, and help shape the future of AI-powered decisioning? Join us.

We are seeking an experienced Software Engineer to help build and enhance cloud-native capabilities within our SaaS platform. This role is primarily focused on developing reliable, scalable Python services and APIs, with opportunities to work on generative AI, intelligent agents, and other emerging AI capabilities.

The ideal candidate has a strong background in backend software development, particularly within a SaaS or cloud-based product environment. Prior experience with large language models, LangChain, retrieval-augmented generation, or AI agents is beneficial but not required. We are looking for engineers who have strong software engineering fundamentals and are interested in applying those skills to modern AI-enabled applications.

This role can be performed remotely. Candidates located in or able to travel to the New York City metropolitan area are preferred and should expect to attend in-person meetings at our New Jersey office approximately once a month.

We are only considering candidates who are authorized to work in the United States without the need for current or future visa sponsorship.

The following experience is valuable but not required:

Building applications that use large language models or generative AI

LangChain, LangGraph, LlamaIndex, or similar AI application frameworks

Developing AI agents that use tools, APIs, or external services

Retrieval-augmented generation, embeddings, and vector search

Amazon Bedrock or other managed AI platforms

Prompt engineering, structured model output, and LLM evaluation

Machine learning model deployment or MLOps practices

Infrastructure as Code using Terraform or CloudFormation

GitHub Actions or similar CI/CD platforms

Designing, developing, testing, and maintaining Python-based backend services and APIs

Building reusable components and platform capabilities for a cloud-native SaaS product

Integrating internal services, external APIs, and third-party platforms

Developing containerized services that run in Kubernetes on AWS

Improving application scalability, resilience, security, monitoring, and operational support

Working closely with product managers, architects, and other engineering teams to deliver customer-facing capabilities

Contributing to software design, code reviews, automated testing, and engineering standards

Supporting services throughout their full lifecycle, from initial design through production operation

Applying generative AI and large language models to new product capabilities where appropriate

Helping develop AI-enabled workflows, intelligent agents, tool integrations, and reusable GenAI platform components

Evaluating emerging AI technologies and determining how they can be safely and effectively incorporated into the platform

Team Fit. A conversation with our Senior Engineering Team to explore how you work, what you're looking for, and how you'd fit with the team

Live Coding: Build an AI Agent. Live session in your language of choice (e.g. Python). You'll build an AI agent from scratch, give it a skill, and get it to complete a real task — we're watching how you think, structure, and debug in real time, not just the output.

Technical Interview. With data science and/or engineering leadership — walk through what you built, why you made the choices you did, and how your approach extends to graph and identity problems, production systems, and team building.