Lead AI Platform Engineer - Agentic AI, Python, Databricks & AWS

Lead AI Engineer

We are looking for a Lead AI Engineer to design, build, and operate enterprise AI solutions. You will help evolve our platform from Retrieval-Augmented Generation (RAG) applications to agentic AI systems that leverage reasoning, orchestration, tool use, and autonomous workflows. You will work closely with platform engineers, architects, and business stakeholders to build scalable, reliable, and measurable AI solutions. A key part of the role is ensuring AI systems can be evaluated, monitored, and operated successfully in production.

Required Education: Bachelor's degree required. Preferred Certification: AWS, Databricks, Microsoft, or AI-related certifications.

Required Qualifications:

• 5+ years of software engineering experience.
• Proven track record of delivering enterprise-grade production software.
• Strong Python development skills.
• Experience building, deploying, and operating production AI systems.
• Experience designing and implementing RAG solutions.
• Experience with Databricks.
• Hands-on experience with LangGraph or similar agent orchestration frameworks.
• Experience building AI workflows that leverage tools, APIs, and external systems.
• Experience with AI evaluation frameworks and quality measurement.
• Experience implementing AI observability and tracing solutions.
• Understanding of agent architecture patterns, prompt engineering, and LLM evaluation techniques.
• Experience with AWS in production environments.
• Experience designing and consuming REST APIs.
• Experience with Git, CI/CD, and modern software engineering practices.
• Knowledge of secure coding principles and responsible AI practices.
• Experience collaborating within Agile software development teams.

Preferred Qualifications:

• Experience with AgentBricks.
• Experience with Microsoft Copilot extensibility and agent development.
• Experience with LangChain and related frameworks.
• Experience with MCP integrations.
• Experience with vector databases and semantic search.
• Experience with AWS Bedrock.
• Experience with OpenTelemetry, LangSmith, Grafana, MLflow, DeepEval, or similar tooling.
• Experience deploying multi-agent systems.
• Experience with Terraform.

Job Responsibilities:

• Lead the design and development of an enterprise AI platform that enables agentic workflows across structured and unstructured data.
• Design, build, deploy, and support production AI solutions.
• Develop agentic workflows, tool integrations, and orchestration pipelines.
• Build and evolve RAG and agent-based architectures.
• Create evaluation frameworks to improve quality, groundedness, and reliability.
• Implement AI observability, tracing, and monitoring capabilities.
• Develop automated testing and regression validation processes.
• Integrate AI solutions with APIs, enterprise applications, and data sources.
• Design reusable AI patterns, frameworks, and components that increase platform scalability and team productivity.
• Establish engineering best practices and contribute to code reviews.
• Research and adopt emerging AI technologies where they provide business value.
• Partner with stakeholders to translate business problems into AI solutions.

**Only those lawfully authorized to work in the designated country associated with the position will be considered.**

**Please note that all Position start dates and duration are estimates and may be reduced or lengthened based upon a client's business needs and requirements.**