Senior AI Engineer REQ_, REQ_

Senior AI Engineer

At 3

Pillar, we leverage cutting-edge technologies to drive innovation and deliver impactful solutions for our clients. As a Senior AI Engineer, you will lead the design and implementation of scalable AI systems and provide technical mentorship to junior team members. You’ll also evaluate model architectures, explore cutting-edge techniques, and ensure solutions are both impactful and ethical.

You will design, build, deploy and run AI agents that automate real business processes across Finance, Partners and Services, Support and beyond. You will take an agent from a messy process description to a governed, monitored, production system that people across the company use every day. You will work directly with our AI Architect and Build Lead. Claude is our primary AI interface, so the craft here sits behind the conversation: getting the right data, orchestrating reliable agent workflows, exposing them as tools, and running them safely in the cloud.

• Build production AI agents end to end: discovery with the process owner, design, prompt and tool engineering, testing, deployment and ongoing operation.
• Collaborate with stakeholders, including business owners, product managers, architects and software engineers, to identify business problems that can be solved with Gen AI and Agentic AI.
• Connect agents to company data through a Snowflake data foundation and directly to source systems such as Net Suite, Salesforce, Zendesk, Asana and Plan Hat.
• Build and maintain MCP servers, tools and Claude skills so agents are available inside Claude where people already work.
• Design data and agent pipelines in Python: retrieval, structured extraction, multi-step orchestration, human-in-the-loop approvals and scheduled runs.
• Implement agent chaining so multiple agents collaborate to solve complex tasks.
• Develop and refine prompts to maximize the performance and accuracy of language models.
• Deploy and operate agents on AWS (Bedrock, Lambda, Step Functions or equivalent) with proper logging, monitoring, cost tracking and alerting.
• Write evaluations that prove an agent is accurate before go-live and keep it accurate afterwards.
• Apply security and data governance by design: least-privilege access, secrets management, PII handling and audit trails.
• Track token and infrastructure spend per agent so value can be reported net of cost.
• Maintain clear and comprehensive technical documentation, and share patterns so the rest of the company can reuse them.
• Mentor and provide technical guidance to junior Python engineers and team members.
• Advocate for AI adoption inside the team, inspiring and supporting others.

• Bachelor's or Master's degree in Computer Science, Engineering, Mathematics or a related field.
• 4-7 years in software or data engineering, with at least 2 years focused on LLM and agent systems in production.
• A track record of building AI agents that run in production. You can walk us through agents you have shipped, the architecture behind them, what broke and how you fixed it.
• Deep working knowledge of agent design methods: tool use and function calling, planning and orchestration patterns, retrieval (RAG), memory and context management, guardrails, and human-in-the-loop design.
• Hands-on experience with LLM APIs (Anthropic Claude preferred; OpenAI or others welcome) and at least one agent framework or SDK such as Claude Agent SDK, Lang Graph, Lang Chain or Llama Index, plus the judgment to know when a framework is not needed.
• Ability to work with different LLM models and choose one over another based on the use case.
• Strong Python, including building APIs (FastAPI), integrations and data pipelines.
• Strong SQL and experience working with a cloud data warehouse,…