AI Engineer — Build Scalable AI for Global Clients

Umain AB; Chicago (IL); On-site; USD 130,000 - 170,000; Full time

Job summary

Umain AB in Chicago’s West Loop is hiring an AI Engineer to build next‑gen AI‑powered products and workflows for global clients. You will combine strong software fundamentals with hands‑on AI capabilities, spanning LLMs, agents, and production pipelines.

You’ll partner with clients, design scalable architectures, implement memory and orchestration, and ship reliable AI systems on Azure, AWS or GCP. This role requires about 8 years of engineering experience, with at least 4 years in AI in

Qualifications

• 8 years engineering experience including at least 4 years building AI-powered systems and shipping AI in production.
• Proven track record delivering robust AI solutions.
• Strong communication across multidisciplinary teams and with clients.

Responsibilities

• Partner with clients to clarify challenges and assess AI feasibility including data security and responsible AI.
• Design, prototype, build, and ship AI-powered applications, workflows, and agents for clients from startups to enterprises.
• Architect agentic systems with context management, memory, orchestration, and tool integrations.
• Select, integrate, and adapt foundation models (OpenAI, Anthropic, Google) and fine-tune when needed.
• Design around model limitations, apply retrieval, embeddings, and UX considerations.
• Build evaluation and observability into every delivery and monitor models, prompts, and agents.

Skills

LLMs

Embeddings

Vector databases

Prompt engineering

Retrieval techniques

Fine-tuning

Model evaluation

Software engineering

TypeScript/Python

Full-stack thinking

Tools

Docker

CI/CD

Azure

GCP

AWS

OpenAI API

Anthropic

Job description

Umain AB in Chicago’s West Loop is hiring an AI Engineer to build next‑gen AI‑powered products and workflows for global clients. You will combine strong software fundamentals with hands‑on AI capabilities, spanning LLMs, agents, and production pipelines.

You’ll partner with clients, design scalable architectures, implement memory and orchestration, and ship reliable AI systems on Azure, AWS or GCP. This role requires about 8 years of engineering experience, with at least 4 years in AI in