Sr. AI Engineer, Agentic Applications

Auditoria.AI•Santa Clara, CA

33d•Onsite

About The Position

We’re looking for an experienced AI Agent Engineer to design, build, and deploy intelligent, autonomous systems that transform how financial operations are automated and optimized. You’ll work with cutting-edge large language models (LLMs) and agent frameworks to build scalable, production-grade AI solutions.

Requirements

Bachelor’s, Master’s, or PhD degree in Computer Science, Machine Learning, or related.
5+ years of software engineering experience, including 2+ years in AI/ML or agentic AI systems.
Expert in Python and modern development practices (async programming, type hints, testing).
Hands-on experience and familiarity with variousLLMs, LangGraph/LangChain, and retrieval-augmented generation (RAG).
Proven ability to integrate AI systems with enterprise APIs and databases.
Experience with observability and monitoring tools (e.g., Langfuse, LangSmith, Arize).
Strong grounding in system design, cloud-native development, and testing practices.
Must be currently authorized to work in the United States without employer sponsorship, as we are unable to sponsor or transfer visas for this position.
Must be located in or within commuting distance of Santa Clara, CA to be considered.

Nice To Haves

Experience with MCP servers/clients, A2A communication, or multi-modal LLMs.
Background in FinTech, enterprise finance systems, or real-time AI applications.
Knowledge of fine-tuning (LoRA, QLoRA, PEFT) and responsible AI best practices.
Familiarity with distributed systems, microservices, and cloud orchestration.

Responsibilities

Design and implement agentic AI systems using Python, LangGraph, and LangChain.
Architect multi-agent frameworks that automate complex financial workflows with human oversight.
Integrate agents with enterprise APIs, databases, and tools using advanced function-calling techniques.
Develop and maintain Model Context Protocol (MCP) servers and Agent-to-Agent (A2A) communication systems.
Evaluate and implement LLMs (GPT, Claude, Gemini, Llama, etc.) based on performance, cost, and capability.
Build RAG pipelines, apply prompt engineering, and incorporate multi-modal LLMs for document understanding.
Implement state machines, memory systems, and adaptive reasoning modules for autonomous behavior.
Ensure observability and reliability with robust monitoring, evaluation, and debugging systems.
Collaborate with cross-functional teams to translate business needs into scalable AI solutions.
Mentor engineers and contribute to internal AI tooling and best practices.