Make sound architectural decisions across microservice and monolithic systems, and integrate AI capabilities into existing client environments.
Evaluate and select models, tools, and frameworks; test and monitor agent quality, safety, cost, and performance.
Document solutions and communicate technical concepts clearly to both technical and non-technical stakeholders.
Required Qualifications
Proven experience working directly with clients, with strong communication and stakeholder-management skills.
Background in business process or workflow analysis in at least one domain such as finance, customer service, or supply chain.
Software development background with experience in both microservices and monolithic architectures.
Proficiency in multiple programming languages, including C# and Python.
Working knowledge of DevOps standards and practices (source control, CI/CD pipelines, infrastructure as code, observability).
Experience building RAG solutions and applying retrieval techniques.
Experience building AI agents on Azure, including Azure AI Foundry.
Hands-on experience with at least one additional major cloud platform (AWS or Google Cloud); working experience with at least two of the three major clouds.
Understanding of agent runtime, orchestration, model selection, and tooling.
Experience delivering enterprise implementations.
Highly organized, self-directed, and able to manage multiple priorities with minimal supervision.
Preferred Qualifications
Experience with agent frameworks and orchestration tools (e.g., Semantic Kernel, LangChain, AutoGen).
Familiarity with vector databases and search platforms (e.g., Azure AI Search, pgvector, Pinecone).
Experience with LLM evaluation, prompt engineering, and responsible AI practices.
Cloud or AI certifications (e.g., Azure AI Engineer, AWS Solutions Architect).
Experience with enterprise security, identity, and compliance requirements.
Core Competencies
Client focus: Builds trust, listens well, and turns business needs into practical solutions.
Technical breadth: Comfortable across languages, clouds, and architectural styles.
Ownership: Takes initiative and drives work from idea to production.
Organization: Plans carefully, tracks details, and delivers on commitments.
Communication: Explains complex AI concepts clearly to varied audiences.