Senior AI Engineer

Eames Consulting Group; United States; On-site; USD 140,000 - 230,000; Full time

Job summary

Eames Consulting Group seeks a Senior AI Engineer to join a product-focused team building next-gen agentic AI experiences in the United States. You will lead backend development, design agent behaviors, and implement robust AI systems for production use.

The role emphasizes hands-on work with Python/Node.js, LLM evaluation, and scalable APIs, ensuring reliability, observability, and performance across services.

Qualifications

• Hands-on backend engineer with production AI experience.
• Deep knowledge of agentic AI systems, tool use, and state management.
• Experience designing and running LLM evaluation frameworks.
• Proficient in Python or Node.js and modern API design.
• Ability to translate business requirements into reliable AI-powered workflows.

Responsibilities

• Design and implement agent behaviors, decision logic, and tool use.
• Build and evolve LLM evaluation frameworks, including prompt regression testing, quality scoring, and failure analysis.
• Develop observability and tracing for AI systems to monitor quality and reliability.
• Design retrieval strategies using vector databases to support agent memory and context.
• Collaborate with AI platform engineers to leverage shared AI infrastructure and capabilities.
• Build and ship customer-facing software, APIs, intelligent workflows, and AI-enabled product capabilities.
• Contribute to backend services, event-driven workflows, and integrations.
• Use AI throughout the software development lifecycle to accelerate development, testing, and debugging.
• Own the quality, reliability, and performance of production systems.

Skills

Backend development

Python

Node.js

LLM evaluation

Agentic AI

Production ML

Observability

Tools

Langfuse

OpenRouter

Pinecone

Redis

Snowflake

AWS

Job description

I’m working with a growing technology organization that is looking for a Senior AI Engineer to join a product-focused engineering team building a new generation of agentic AI experiences.

This is a hands-on, backend-leaning role for an engineer with strong experience building, evaluating, and running AI agents in production. You’ll work closely with engineering, data science, and business stakeholders to turn complex workflows into reliable, intelligent systems.

What you’ll be doing:

• Design and implement agent behaviors, decision logic, and tool use
• Build and evolve LLM evaluation frameworks, including prompt regression testing, quality scoring, and failure analysis
• Develop observability and tracing for AI systems to monitor quality and reliability
• Design retrieval strategies using vector databases to support agent memory and context
• Collaborate with AI platform engineers to leverage shared AI infrastructure and capabilities
• Build and ship customer-facing software, APIs, intelligent workflows, and AI-enabled product capabilities
• Contribute to backend services, event-driven workflows, and integrations
• Use AI throughout the software development lifecycle to accelerate development, testing, and debugging
• Own the quality, reliability, and performance of production systems

What we’re looking for:

• Strong software engineering fundamentals and sound engineering judgment
• Deep hands-on experience with agentic AI systems — including how agents reason, use tools, manage state, and handle failure
• Experience designing and running LLM evaluation frameworks
• Strong backend experience with Python or Node.js
• Experience building and scaling modern applications, services, or APIs
• Ability to translate business requirements and domain knowledge into structured agent behavior
• Comfortable working alongside data scientists and turning analytical outputs into production-ready systems
• Strong problem-solving, communication, and collaboration skills
• Builder mindset with the ability to work through ambiguity and iterate quickly
• Experience with fintech, insurtech, or other highly regulated environments is a plus

Python, TypeScript, Node.js, Langfuse, OpenRouter, Pinecone, Redpanda, PostgreSQL, Redis, Snowflake, AWS, and modern cloud infrastructure.

Important:

• US Citizens and Green Card holders only
• No visa sponsorship or transfers available
• No third-party agencies or C2C submissions