Senior AI Engineer

The Senior AI Engineer role supports Altimetrik Corp in Chicago, IL (hybrid) by designing, building, and validating moderate to complex AI and ML application solutions. The position includes work with LLMs and agent development on Google Vertex AI.

Key Responsibilities

• Evaluate defined client area requirements and processes, including new enhancements or maintenance, then review detailed designs and develop moderate to complex application program solutions.
• Maintain solution quality through peer code reviews, documentation, implementation, program logic verification, defect root cause analysis, and unit and integration testing.
• Participate in systems testing in collaboration with other IT staff.
• Support high-level solution design activities.
• Consult with the client area to analyze system requirements and capabilities, identify associated risks, and resolve problems.
• Serve as a liaison between client stakeholders and application areas when needed.
• Research and evaluate new and/or alternative solutions, then recommend efficient and cost-effective approaches for systems and program design, including developing system specifications and procedures.
• When applicable, integrate vendor applications and consulting resources into existing applications and resources.
• Coordinate with operations technical staff to support implementation of applications into production and testing environments.
• Collaborate with technical personnel to identify and resolve issues.

Required Skills and Qualifications

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

Technologies

• 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 Arrangement

Chicago, IL (Hybrid) with 3 days onsite. Work location is in person.

Benefits

• Relocation assistance