SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
AppZen is the leader in autonomous spend-to-pay software, using patented AI to process information from thousands of data sources and help organizations understand enterprise spend at scale. The company's invoice, expense, and card transaction solutions are used by one-third of the Fortune 500 to replace manual finance processes.
You will join the growing AI team as an AI/ML Engineer to build and ship LLM-powered and agentic features that read, understand, and make decisions on invoices, expense reports, and card transactions for some of the world's largest finance teams. You will work alongside senior AI/ML engineers, data scientists, and product managers to take features from prototype to production and own them once live.
Key responsibilities include:
• LLM & Agent Development: Build and improve LLM-powered features and multi-step agentic workflows (e.g., using LangGraph) that extract, validate, and reason over invoices, receipts, expense reports, and card transactions.
• Retrieval-Augmented Generation (RAG): Build retrieval pipelines (chunking, embeddings, vector search, re-ranking) that give models the right policy, vendor, and transaction context to make accurate financial decisions.
• Tool Use & Structured Outputs: Implement function calling and API integrations so models can reliably query internal services and ERP/AP systems, and return validated, structured (JSON) outputs.
• Evaluation & Quality: Build evaluation datasets, metrics, and automated test suites to measure accuracy, hallucination rate, latency, and cost, and use results to improve prompts, retrieval, and models.
• Production Engineering: Package and deploy models and services using Docker and CI/CD pipelines, add monitoring and logging, and keep them reliable, scalable, and cost-efficient in production.
• Cross-functional Collaboration: Work closely with senior engineers, data scientists, and product managers to turn customer and business requirements into well-scoped technical solutions, and contribute to code reviews and design discussions.
REQUIREMENTS:
• Professional Experience: 1–3 years of experience building and deploying ML/AI solutions in production, including at least 1 year of hands-on work on LLM-based applications.
• Programming: Strong Python skills, with experience writing clean, tested, production-grade code and building REST APIs (e.g., FastAPI or Flask).
• LLM & Agent Frameworks: Hands-on experience with LangChain, LangGraph, LlamaIndex, or similar frameworks, and with LLM APIs (e.g., OpenAI, Anthropic, Gemini) or open-source models.
• RAG & Vector Databases: Practical experience building RAG pipelines using vector databases such as Pinecone, Milvus, pgvector, or FAISS.
• Prompting & Structured Outputs: Good understanding of prompting techniques (few-shot, Chain-of-Thought, ReAct) and of getting reliable structured outputs and function calls from LLMs.
• ML Fundamentals: Solid grounding in ML and NLP fundamentals, with working experience in PyTorch or a similar framework. Exposure to fine-tuning (e.g., LoRA) is a plus.
• MLOps & Cloud: Working knowledge of Docker, Git, and CI/CD, and experience deploying on a cloud platform (AWS, GCP, or Azure). Familiarity with LLM observability tools (e.g., LangSmith, Arize Phoenix, or Weights & Biases) is a plus.
• Good to Have: Experience with document AI (OCR, invoice or receipt data extraction) or with finance, accounts payable, or expense data.
• Education: Bachelor's or Master's degree in Computer Science, Engineering, or a related technical field, or equivalent practical experience.
