Senior AI/ML Engineer

About the Role:

• We are looking for a Senior AI/ML Engineer to join our growing AI stack team. In this role, you will be a key individual contributor responsible for evolving our platform from static LLM implementations to autonomous agentic workflows. You will work alongside highly skilled data scientists and engineers to build systems that don’t just process data, but reason, use tools, and solve complex financial problems independently. If you are passionate about the intersection of Natural Language Understanding and autonomous agency, AppZen is the place for you.

Key Responsibilities:

• Agentic System Design: Design and implement autonomous agents capable of task decomposition, reasoning (Chain-of-Thought), and self-correction. You will build systems that move beyond simple prompts into complex, multi-step agentic workflows.
• Tool Orchestration & Integration: Develop robust interfaces for LLMs to interact with external APIs, databases, and financial tools. You will be responsible for ensuring reliable function calling and tool-use accuracy within our spend-to-pay ecosystem.
• Advanced LLM Implementation: Lead the integration of state-of-the-art LLMs, focusing on Retrieval-Augmented Generation (RAG) and long-term memory management to provide agents with the context necessary for high-stakes financial decision-making.
• MLOps & Production Engineering: Architect and manage advanced MLOps pipelines for continuous integration, continuous delivery (CI/CD), model serving, monitoring, and automated retraining. You'll ensure the reliability, scalability, and efficiency of all ML services.
• Cross-functional Collaboration: Work closely with product managers, software engineers, and data scientists to translate business requirements into technical solutions and seamlessly integrate AI/ML models into our core platforms.

Required Skills & Experience:

• Professional Experience: 4+ years of experience building and deploying AI/ML solutions in production, with at least 1 year of focused experience in LLM application development.
• Agentic Frameworks: Hands-on experience with orchestration frameworks such as LangGraph, CrewAI, AutoGen, or LangChain.
• Reasoning & Prompt Engineering: Deep understanding of advanced prompting techniques (ReAct, Chain-of-Thought, Tree-of-Thought) and experience fine-tuning models specifically for function calling or structured output (JSON).
• Programming & Frameworks: You are an expert in Python (and ideally familiar with Golang) with extensive experience using PyTorch to solve complex ML problems. You understand how to bridge the gap between LLMs and data, utilizing vector databases like Pinecone or Milvus to provide agents with the "semantic memory" required for high-context, multi-step tasks.
• System Design: Proven ability to design microservices and distributed systems that handle high-volume data processing. You understand how to manage state in long-running agentic tasks.
• MLOps & DevOps: Proficient with Docker, Kubernetes, and CI/CD pipelines. Experience with LLM-specific monitoring tools (e.g., LangSmith, Arize Phoenix, or Weights & Biases) is highly preferred.
• Education: Bachelor's or Master's degree in Computer Science, Engineering, or a related technical field, or equivalent practical experience.