AI Engineer

Asterism IT Solutions; Illinois; On-site; USD 140,000 - 170,000; Full time

Job summary

Asterism IT Solutions is seeking an experienced AI Engineer in the United States for hands-on Prompt Engineering, LLM application development, Agentic AI, and RAG workflows. You will design reliable, context-aware AI solutions, integrate LLMs with enterprise systems, and improve model response quality and safety.

The role emphasizes secure data handling, governance, and collaboration with product, architecture, and engineering teams to deploy production-ready AI agents and MCP-enabled workflows.

Qualifications

• 9+ years of professional IT/software engineering experience.
• Strong hands-on Prompt Engineering experience with templates, system prompts, and tuning.
• Hands-on experience with LLMs such as GPT, Claude, Gemini, Llama, or similar models.
• Experience developing AI applications using LLM APIs, RAG workflows, enterprise data sources, and backend services.
• Strong programming experience with Python, JavaScript, or similar languages.
• Knowledge of RAG, embeddings, vector databases, semantic search, and knowledge retrieval workflows.
• Understanding of NLP, hallucination mitigation, prompt-injection risks, guardrails, and responsible AI.
• Experience integrating AI solutions with APIs, backend services, and enterprise systems.
• Knowledge of healthcare data privacy and secure handling incl. HIPAA-aligned practices, PHI/PII protection, data minimization, de-identification, data masking, access controls, auditability, and responsible use of healthcare data in AI workflows.

Responsibilities

• Design, develop, and optimize prompts for LLMs to improve accuracy and business outcomes.
• Build Agentic AI solutions supporting planning, reasoning, memory, and multi-step task execution.
• Develop MCP tools enabling AI agents to securely interact with enterprise systems, APIs, and data sources.
• Design agent architectures, tool-calling frameworks, retrieval mechanisms, and context-management strategies.
• Develop AI-powered applications using LLM APIs, RAG workflows, enterprise data sources, and backend services.
• Implement Retrieval-Augmented Generation, knowledge grounding, embeddings, vector databases, and semantic search.
• Evaluate and improve LLM responses for accuracy, relevance, completeness, tone, and instruction following.
• Develop evaluation frameworks and prompt-testing methodologies to measure AI agent performance, quality, and reliability.
• Apply NLP concepts, hallucination mitigation techniques, prompt-injection protection, guardrails, and responsible AI practices.
• Collaborate with product managers, architects, and engineering teams to translate business requirements into AI-driven solutions.
• Ensure AI solutions follow security, compliance, governance, and responsible AI standards.
• Support deployment, monitoring, troubleshooting, and continuous improvement of AI agents and MCP-enabled workflows.
• Contribute to architecture reviews, technical design documentation, and AI engineering best practices.

Skills

Prompt Engineering

LLMs

Python

APIs & Backend

RAG

NLP

Security & HIPAA

Tools

MCP servers

Agentic AI framework

Job description

We are seeking an experienced AI Engineer with strong hands-on experience in Prompt Engineering, LLM application development, Agentic AI, RAG, and AI response optimization.

The ideal candidate will have experience designing reliable, context-aware AI solutions, integrating LLMs with enterprise systems, developing AI agents and tool-calling workflows, and improving model response quality, accuracy, and reliability.

Key Responsibilities

• Design, develop, and optimize prompts for Large Language Models (LLMs) to improve accuracy, reliability, and business outcomes.
• Build and configure Agentic AI solutions supporting planning, reasoning, memory, and multi-step task execution.
• Develop and integrate MCP (Model Context Protocol) tools that enable AI agents to securely interact with enterprise systems, APIs, and data sources.
• Design agent architectures, tool-calling frameworks, retrieval mechanisms, and context-management strategies.
• Develop AI-powered applications using LLM APIs, RAG workflows, enterprise data sources, and backend services.
• Implement Retrieval-Augmented Generation (RAG), knowledge grounding, embeddings, vector databases, and semantic search.
• Evaluate and improve LLM responses for accuracy, relevance, completeness, tone, and instruction following.
• Develop evaluation frameworks and prompt-testing methodologies to measure AI agent performance, quality, and reliability.
• Apply NLP concepts, hallucination mitigation techniques, prompt-injection protection, guardrails, and responsible AI practices.
• Collaborate with product managers, architects, and engineering teams to translate business requirements into AI-driven solutions.
• Ensure AI solutions follow security, compliance, governance, and responsible AI standards.
• Support deployment, monitoring, troubleshooting, and continuous improvement of AI agents and MCP-enabled workflows.
• Contribute to architecture reviews, technical design documentation, and AI engineering best practices.

Required Skills

• 9+ years of professional IT/software engineering experience.
• Strong hands-on Prompt Engineering experience, including prompt templates, system prompts, few-shot prompting, and response tuning.
• Hands-on experience with LLMs such as GPT, Claude, Gemini, Llama, or similar models.
• Experience developing AI applications using LLM APIs, RAG workflows, enterprise data sources, and backend services.
• Strong programming experience with Python, Java, JavaScript, or similar languages.
• Knowledge of RAG, embeddings, vector databases, semantic search, and knowledge retrieval workflows.
• Experience evaluating and optimizing LLM responses.
• Understanding of NLP, hallucination mitigation, prompt injection risks, guardrails, and responsible AI.
• Experience integrating AI solutions with APIs, backend services, and enterprise systems.
• Knowledge of healthcare data privacy and secure sensitive-data handling, including:
  • HIPAA-aligned practices
  • PHI/PII protection
  • Data minimization
  • De-identification
  • Data masking
  • Access controls
  • Auditability
  • Responsible use of healthcare data in AI workflows

Preferred Skills

• Experience with MCP servers / Model Context Protocol.
• Experience building and deploying Agentic AI solutions in production.
• Experience with cloud platforms and production AI deployments.
• Experience integrating AI agents with healthcare systems, electronic health records, or other regulated-industry systems.
• Experience with healthcare data and regulated enterprise environments.
• Experience with AI evaluation frameworks and automated prompt testing.
• Experience with AI architecture, technical design, and production monitoring.