AI Architect

About the role

You will join SoftServe’s Autonomous Agentic Platform, Neo, to design and deliver scalable AI‑centric solutions. The role translates ambiguous business and technical needs into robust architectures, engineering standards, and production‑ready implementations.

Key responsibilities

• Shape the technical direction of a production‑grade Autonomous Agentic Platform.
• Define reusable agentic patterns, contracts, interfaces, workflows, and delivery slices for the Agentic SDLC.
• Lead implementation strategy across agent workflows, MCP tools, context pipelines, orchestration patterns, and platform services.
• Partner with architects, product owners, and client stakeholders to turn vision into executable technical systems.
• Make high‑impact technical decisions balancing speed, quality, scalability, reliability, and client delivery needs.
• Establish engineering standards for code quality, testing, observability, documentation, operational readiness, and workflow governance.
• Mentor technical leads and engineers, clarifying architecture and raising quality standards.
• Use metrics, benchmarking, and validation evidence to improve platform reliability, agent performance, and delivery quality.
• Advance Neo’s technical voice through papers, conference talks, client‑facing thought leadership, and internal enablement.

Required profile

• 10+ years designing, building, and scaling complex software platforms, especially AI‑centric, distributed, event‑driven, or autonomous systems.
• Proven leadership experience guiding engineers and cross‑functional teams through complex technical decisions and production‑grade outcomes.
• Evidence‑driven approach using metrics, benchmarking, and operational insights to improve system reliability.
• Strong understanding of architecture fundamentals such as microservices, C4 modeling, design patterns, and contract‑first engineering.

Required skills

• Python
• TypeScript / JavaScript
• React
• Node.js
• REST / OpenAPI service contracts
• MCP integration
• Cloud‑native deployment patterns
• CI/CD pipelines
• Observability and automated testing
• AI/ML engineering with LLM‑based systems, agentic workflows, retrieval and indexing strategies
• Context engineering, evaluation methodologies, token‑budget management