AI Engineer

STG; Salt Lake City (UT); On-site; USD 120,000 - 170,000; Full time

Job summary

STG is seeking a versatile AI Engineer to design, evaluate, and operate intelligent systems built on foundation models. You will architect autonomous agents, ground AI responses in enterprise data, and ensure scalable, secure, and context‑aware solutions.

You will work with LangGraph, AutoGen, or CrewAI and deploy in AWS/Azure/GCP, focusing on human‑in‑the‑loop interfaces and safety controls to meet global regulations.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, or a related field.
• Expertise in Python and TypeScript; Go/Rust a plus for high‑performance services.
• Deep experience with orchestration libraries like LangChain, LlamaIndex, and agentic frameworks.
• Strong understanding of embedding models, chunking, and large‑scale data handling.
• Proficiency with Docker/Kubernetes and ML lifecycle CI/CD (MLOps/LLMOps).
• Experience building secure, type‑safe APIs (REST/GraphQL/tRPC).
• Ability to translate complex AI behaviors into clear business insights.

Responsibilities

• Design multi-agent systems for autonomous planning, tool selection, and self‑reflection.
• Build and optimize RAG pipelines using vector databases and advanced hybrid search.
• Connect AI agents to internal tools and third‑party APIs via MCP.
• Evaluate foundation models and open‑source variants for cost, latency, and accuracy.
• Deploy AI apps in cloud environments with monitoring for model drift and token costs.
• Collaborate with product and frontend teams to create Human‑in‑the‑Loop interfaces.
• Implement deterministic guardrails for bias, privacy, and compliance with AI regs.

Skills

Python

TypeScript

Go

Rust

CI/CD

APIs

LLMOps

MLOps

problem solving

communication

Education

Bachelor’s or Master’s degree in CS/AI or related field

Tools

LangChain

LlamaIndex

AutoGen

CrewAI

Docker

Kubernetes

AWS

Azure

GCP

Job description

We are seeking a versatile and innovative AI Engineer to join our engineering team. The role of an AI Engineer has evolved from simple model integration to the architecture of autonomous agentic systems and complex reasoning workflows. You will be responsible for designing, evaluating, and operating intelligent systems built on foundation models, ensuring they are scalable, secure, and context-aware. This role bridges the gap between cutting‑edge AI research and production‑grade software engineering, delivering high‑impact solutions that automate reasoning and enhance human productivity across diverse industries.

Your Role

Responsibilities:

• Design and implement multi-agent systems capable of autonomous planning, tool selection, and self-reflection using frameworks like LangGraph, AutoGen, or CrewAI.
• Build and optimize Retrieval-Augmented Generation pipelines using Vector Databases (Pinecone, Weaviate, Milvus) and advanced hybrid search techniques to ground AI responses in enterprise data.
• Leverage the Model Context Protocol (MCP) to connect AI agents to internal tools, secure data sources, and third‑party APIs seamlessly.
• Conduct rigorous evaluations of foundation models (e.g., GPT-5, Claude 4, Gemini 2) and fine‑tuned open‑source models to ensure the best balance of cost, latency, and accuracy.
• Deploy and manage AI applications in cloud-native environments (AWS, Azure, GCP), implementing automated monitoring for "model drift," hallucination rates, and token cost optimization.
• Work with product owners and frontend engineers to design intuitive "Human-in-the-Loop" interfaces that allow users to safely steer and review AI outputs.
• Implement deterministic guardrails and safety controls to prevent bias, ensure data privacy, and maintain compliance with global AI regulations.

Qualifications:

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, or a related technical field.
• Mastery of Python and TypeScript, with experience in Go or Rust considered a plus for high‑performance inference services.
• Deep experience with orchestration libraries such as LangChain, LlamaIndex, and specialized agentic frameworks.
• Strong understanding of embedding models, chunking strategies, and managing large‑scale unstructured data.
• Proficiency with containerization (Docker, Kubernetes) and CI/CD pipelines, specifically adapted for machine learning lifecycles (MLOps/LLMOps).
• Expertise in building secure, type‑safe APIs (REST, GraphQL, or tRPC) that serve as the interface for AI‑powered features.
• Ability to translate complex "black box" AI behaviors into clear technical and business insights for stakeholders.

Nice to Have:

• Expert proficiency in using AI-native IDEs and tools like Cursor or GitHub Copilot to accelerate the SDLC.
• Experience with OpenTelemetry for tracing complex, multi‑step AI reasoning chains.
• Specialized knowledge in optimizing token usage, caching strategies, and managing inference costs at scale.
• Specialized AI certifications from major cloud providers (e.g., AWS Certified AI Practitioner or Azure AI Engineer Associate).