Senior Staff AI Software Engineer

Summary

Join Oportun's dynamic team as a Senior Staff AI Engineer and lead the design and implementation of cutting-edge AI solutions, including GenAI, RAG, and NLP-based systems. You will play a critical role in identifying business challenges and crafting scalable, production-ready AI applications. As a Senior Staff AI Engineer, you will drive the development of intelligent systems spanning document understanding, conversational interfaces, recommendation engines, and cognitive automation. You will collaborate with data scientists, machine learning engineers, product managers, and engineering leaders to establish best practices and a strategic roadmap for enterprise-wide AI adoption. You will guide the end-to-end lifecycle, from prototyping and experimentation to robust system integration and deployment. Oportun seeks a hands-on, business-minded engineer who can design technically sound architectures and deliver AI-powered solutions to real-world problems.

Requirements

• 15+ years of experience in software, ML, or AI engineering; with at least 3+ years working directly on LLMs or AI applications
• Strong experience with LLM APIs (e.g., OpenAI, Anthropic, Cohere), open-source models (e.g., LLaMA, Mistral, Mixtral), and deployment stacks
• Experience with prompt engineering, prompt templates, system message design, and evaluation/testing strategies for LLM behavior
• Deep knowledge of retrieval pipelines, vector databases (e.g., ChromaDB, Pinecone, FAISS, Weaviate), and embedding strategies
• Hands-on experience with LangChain, LlamaIndex, or similar AI orchestration frameworks
• Expertise in building scalable APIs and AI application backends using Python, FastAPI, or Node.js
• Solid understanding of cloud infrastructure (AWS/GCP/Azure) and deployment of AI apps using Docker, Kubernetes, and serverless technologies
• Familiarity with AI safety, ethics, and responsible AI principles in real-world deployments
• Strong communication skills with the ability to translate complex AI capabilities into business impact
• Thorough comprehension of software engineering principles, version control (Git), and collaborative development workflows
• Track record of successfully integrating DevOps practices, continuous integration, and continuous deployment (CI/CD) pipelines
• Exceptional communication aptitude, capable of fostering effective collaboration across diverse teams and stakeholders

Responsibilities

• Define and lead the AI applications strategy—designing scalable, production-grade systems leveraging Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and multi-modal AI for high-impact business use cases
• Collaborate with product managers, data scientists, and engineering leaders to identify opportunities for AI integration across business domains such as customer service automation, document understanding, personalization, and internal tooling
• Architect, prototype, and scale AI-driven applications by orchestrating LLMs, vector databases, embedding models, and prompt chaining frameworks
• Establish best practices for prompt engineering, system prompts, fine-tuning strategies, evaluation frameworks, and safety alignment
• Design and deploy robust RAG pipelines integrated with structured and unstructured data sources using tools like LangChain, Haystack, or custom frameworks, leveraging vector stores such as ChromaDB for semantic retrieval
• Champion a developer-friendly AI platform architecture, focusing on modularity, reproducibility, governance, and compliance
• Integrate MLOps and AIOps principles for AI applications, ensuring observability, explainability, and responsible AI practices
• Mentor engineers across disciplines on effective LLM usage, GenAI techniques, prompt design, and evaluation
• Stay abreast of industry developments in GenAI, agentic systems, tool use/function calling, and multi-agent orchestration—and bring in cutting-edge innovations where feasible