Principal AI Engineer

AltexSoft is a company focusing on AI-native software delivery, working on international projects and providing training budgets.

• Deep software engineering and architecture expertise including system design, testing, refactoring, and code review capable of evaluating AI output.
• Demonstrable AI-first delivery experience with production work through agentic tools.
• Fluency with modern AI coding environments including Claude Code, Cursor or equivalents, with plan and agent modes.
• Specification-driven, context-engineering discipline with problem framing and design prior to agent execution.
• Ability to identify and manage hallucinated APIs, logic errors, and LLM antipatterns in generated code.
• Strong English communication skills for client and distributed team collaboration.
• Autonomous work style with ownership for outcomes, including agent-produced results.
• Business-oriented decision making optimizing client and business outcomes.
• Decisiveness under ambiguity and pragmatic approach favoring quality and speed.
• Strong communication skills to explain technical decisions to diverse audiences.
• Mentorship capabilities to support team members beyond individual contribution.

• Own end-to-end delivery of complex features and services through an agentic, specification-driven workflow, with architecture and acceptance criteria defined up front and AI executing the build under your direction.
• Architect systems that are legible to both humans and agents, making design and tooling decisions that enable AI-first delivery.
• Orchestrate AI coding agents (e.g., Claude Code, Cursor agent layer, Kiro) for targeted edits, refactors, and builds; select the right tool for each task.
• Practice agentic TDD: ensure tests and specifications drive the agent, engineering quality in from the start.
• Conduct AI-first code reviews on agent-generated changes before human review to manage reviewer workload.
• Apply spec-driven frameworks such as BMAD, OpenSpec, and Superpowers, choosing approaches based on project parameters.
• Manage token and cost economics of agentic delivery as an engineering constraint.
• Shape AltexSoft's AI-native SDLC practices and mentor teams transitioning from manual to AI-first delivery.
• Maintain human judgment in architecture, security, ambiguous requirements, and final quality decisions.