AI Engineer

Eliassen Group; United States; Remote; USD 124,000 - 152,000; Full time

Job summary

Eliassen Group is hiring a Software Engineer to join a two-person AI enablement pod and co-build LLM-powered features, embedded with solution teams to deliver reusable capabilities and production-ready services.

You will work with a senior AI Solutions Architect, product managers, and platform teams to design and implement end-to-end AI features, emphasizing reliability and efficient evaluations. This is a remote role with W-2 benefits and a competitive rate.

Qualifications

• 3+ years of professional software engineering.
• Backend experience in .NET or Java with working familiarity in Python.
• Hands-on experience delivering LLM-powered features such as RAG, tool calling, prompt engineering, and structured outputs.
• Experience with Azure, REST APIs, Git, and CI/CD.
• Comfortable with React, Angular, or TypeScript.
• Demonstrated ability to onboarding quickly into a new codebase within 6–8 weeks.

Responsibilities

• Build and ship LLM-powered features including RAG pipelines, tool-calling agents, multi-step workflows, and prompt frameworks.
• Integrate solutions with the AI middleware platform and contribute reusable capabilities.
• Implement evaluation and testing for AI outputs including test sets, automated checks, regression detection, and quality gates.
• Develop APIs, backend services, integrations, and UI components required for AI features.
• Add observability, logging, and cost tracking to deployed AI systems and remediate issues.
• Pair with solution team engineers to enable independent execution of AI feature development.
• Document designs, decisions, and lessons to accelerate future teams.

Skills

3+ years experience

Backend: .NET/Java

Python familiarity

REST APIs

CI/CD

Frontend: React/TS

Tools

Azure

Git

Terraform

Langfuse

Job description

Description:

Remote

Our client is modernizing its platform with AI-native capabilities. You will be the second engineer in a two-person enablement pod, embedded with solution teams to co-build LLM-powered features and transfer knowledge. You will partner with a senior AI Solutions Architect and collaborate with product managers, engineers, and the AI platform team to deliver reusable capabilities, reliable evaluations, and production-ready services.

Due to client requirements, applicants must be willing and able to work on a w2 basis. For our w2 consultants, we offer a great benefits package that includes Medical, Dental, and Vision benefits, 401k with company matching, and life insurance.

Rate: $90.00 to $110.00/hr. w2

Responsibilities:

• Build and ship LLM-powered features including RAG pipelines, tool-calling agents, multi-step workflows, and prompt frameworks.
• Integrate solutions with the AI middleware platform and contribute reusable capabilities.
• Implement evaluation and testing for AI outputs including test sets, automated checks, regression detection, and quality gates.
• Develop APIs, backend services, integrations, and UI components required for AI features.
• Add observability, logging, and cost tracking to deployed AI systems and remediate issues.
• Pair with solution team engineers to enable independent execution of AI feature development.
• Document designs, decisions, and lessons to accelerate future teams.

Experience Requirements:

• 3+ years of professional software engineering.
• Backend experience in .NET or Java with working familiarity in Python.
• Hands-on experience delivering LLM-powered features such as RAG, tool calling, prompt engineering, and structured outputs.
• Experience with Azure or comparable cloud, REST APIs, Git, and CI/CD.
• Comfortable with a modern front end such as React, Angular, or TypeScript.
• Demonstrated curiosity and ability to become productive in a new codebase and business within 6 to 8 weeks.
• Preferred: Azure OpenAI, Azure Container Apps, Terraform.
• Preferred: Vector databases and semantic search.
• Preferred: Exposure to eval frameworks, LiteLLM, Langfuse, or similar.
• Preferred: Event-driven architectures.
• Preferred: Financial systems or payments exposure.