Artificial Intelligence Engineer

LaunchCode; Missouri; On-site; USD 120,000 - 180,000; Full time

Job summary

LaunchCode is seeking an AI Engineer to design, develop, and deploy AI-powered features across enterprise environments. You will build production-grade LLM integrations, RAG pipelines, and agentic systems that deliver measurable business value.

You will collaborate with product, engineering, and data teams to identify high-impact opportunities, implement structured prompts, and optimize observability, performance, and cost management across AI solutions.

Qualifications

• 1–4 years of experience in software or applied AI
• Hands-on with at least two major LLM providers (OpenAI, Anthropic, Azure OpenAI)
• Proficiency with Copilot Studio, Azure Foundry, and Databricks Genie
• Strong Python development for API integration and orchestration
• Experience building RAG pipelines with embeddings and vector search
• Understanding of agentic system design and tool use
• Familiarity with ML Ops concepts like monitoring and logging
• Experience with cloud platforms (Azure preferred)
• Ability to contribute to production codebases and CI/CD workflows

Responsibilities

• Build AI-powered features using Copilot, Azure Foundry, OpenAI, Anthropic, and Databricks Genie
• Develop RAG pipelines connecting LLMs to enterprise data sources
• Design AI agents for multi-step reasoning, planning, and tool use
• Create structured prompts, system instructions, and orchestration logic
• Build evaluation harnesses for accuracy, latency, cost, and safety
• Integrate LLM APIs into backend services and apps
• Monitor and optimize production AI systems, including observability and cost control
• Collaborate with product, engineering, and data teams to identify high-impact AI opportunities
• Document pipelines, prompts, evaluation results, and architectural decisions

Skills

Python

LLM integration

RAG pipelines

CI/CD

Azure

Tooling and prompts

Tools

Copilot Studio

Azure AI Foundry

Databricks Genie

OpenAI

Job description

The role will work closely with our team as we take on projects across multiple divisions, providing technical expertise and strategic guidance to identify where AI can deliver meaningful business value. This individual would help evaluate opportunities to enhance existing processes, automate manual tasks, improve decision-making, and develop scalable solutions that align with business objectives. In addition to supporting project solutioning efforts, the role would collaborate with stakeholders to determine when AI is the right fit for a given challenge and help design, implement, and optimize those solutions. This could include leveraging agentic AI capabilities, developing intelligent workflows, integrating AI-driven tools into existing systems, or utilizing platforms such as Databricks to build and manage data and AI solutions. The position would play a key role in connecting business needs with emerging technologies, ensuring we are effectively incorporating AI where it can drive efficiency, innovation, and measurable results.

The AI Engineer is responsible for designing, developing, and deploying AI-powered features

using leading enterprise AI platforms. This role focuses on building production-grade LLM

integrations, evaluation frameworks, and agentic systems that deliver measurable business value. The ideal candidate has hands‑on experience with commercial foundation models and is

comfortable working across multiple AI ecosystems, including Microsoft Copilot, Azure AI

Foundry, Databricks Genie, Anthropic Claude, and OpenAI GPT models.

Key Responsibilities

• Build and deploy AI-powered product features using Copilot, Azure AI Foundry, OpenAI, Anthropic, and Databricks Genie.
• Develop Retrieval-Augmented Generation (RAG) pipelines that connect LLMs to enterprise data sources.
• Design and implement AI agents capable of multi‑step reasoning, planning, and tool use.
• Create structured prompts, system instructions, and orchestration logic for reliable model behavior.
• Build evaluation harnesses to measure accuracy, latency, cost, and safety of AI systems.
• Integrate LLM APIs into backend services and enterprise applications.
• Monitor and optimize production AI systems, including observability, performance tuning, and cost management.
• Collaborate with product, engineering, and data teams to identify high-impact AI opportunities.
• Document pipelines, prompts, evaluation results, and architectural decisions.

Required Skills & Qualifications

• 1–4 years of experience in software engineering, machine learning engineering, or applied AI.
• Hands‑on experience with at least two major LLM providers (OpenAI, Anthropic, Azure OpenAI).
• Proficiency with Microsoft Copilot Studio, Azure AI Foundry, and familiarity with Databricks Genie.
• Strong Python development skills for API integration and orchestration.
• Experience building RAG pipelines using embeddings, vector search, and grounding strategies.
• Understanding of agentic system design, including tool use and structured outputs.
• Familiarity with ML Ops concepts such as monitoring, logging, and model lifecycle management.
• Experience with cloud platforms (Azure preferred).
• Ability to work in production codebases and contribute to CI/CD workflows