Senior AI Engineer

Altimetrik Corp is hiring a Senior AI Engineer (Google ADK) in Chicago, IL for a hybrid role with 3 days onsite. The position focuses on building, reviewing, and validating moderate to complex AI and ML solutions, including LLM and agent development using Google Vertex AI.

Key Responsibilities

• Evaluate client area requirements and processes (including new enhancements or maintenance), review detailed designs, and develop moderate to complex application program solutions.
• Maintain solution quality through peer code review, documentation creation, code implementation, program logic verification, defect root cause analysis, and unit and integration testing.
• Participate in systems testing activities with other IT staff.
• Contribute to high-level solution design.
• Consult with the client area to analyze system requirements and capabilities, identify associated risks, and resolve issues.
• Serve as a liaison between clients and the applications area when needed.
• Research and evaluate new and/or alternative solutions, recommend the most efficient and cost-effective approach for system/program design, and develop system specifications and procedures.
• Support potential integration of vendor applications and consulting resources into existing applications and resources.
• In coordination with operations area technical staff, support implementation of the application into production and testing environments.
• Confer with technical personnel to identify and resolve technical issues.

Required Qualifications

• Senior-level proficiency in Python with experience in AI/ML development.
• Strong understanding of Large Language Models (LLMs) and their operational mechanics.
• Experience developing AI Agents on Google Vertex AI using Gemini or OpenAI.
• Expertise in Prompt Engineering Best Practices.
• Google Agent Development Kit (Google ADK).
• Experience with LangChain and LangGraph.
• Knowledge of Context Filtering and Prompting Security Best Practices.
• Familiarity with observability and debugging tools: LangSmith, LangFuse, and Phoenix or Arize.
• Experience with Eval AI testing and model evaluation workflows.

Technology Focus

• Python, AI/ML, Large Language Models (LLMs)
• Google Vertex AI, Gemini, OpenAI
• Google Agent Development Kit
• LangChain, LangGraph
• Context Filtering, Prompting Security Best Practices
• LangSmith, LangFuse, Phoenix, Arize
• Eval AI

Location and Work Model

Chicago, IL (Hybrid) with 3 days onsite. Work Location: In person.

Benefits

• Relocation assistance