[Hiring] Senior AI-Native Software Engineer @EPAM Systems

Role Description

We're looking for Senior Software Engineers to join small AI-native teams where AI coding agents are the default way to build software, whether that's web applications, APIs, data pipelines, modernization solutions, or agentic systems for clients. This role is about engineering with AI agents, not just building them. You'll use AI coding agents as an integral part of your daily development workflow, contribute to technical decisions, ensure production-quality delivery, and collaborate directly with client stakeholders.

Responsibilities

• Design, develop, and deliver software solutions using AI coding agents across the entire development lifecycle, from problem analysis and specifications to production.
• Apply agentic SDLC practices, including spec-driven development, agent configuration, parallel and background agent execution, code review, and quality gates.
• Configure and optimize repositories for AI coding agents using repository instructions, prompt files, skills, custom agents, subagents, and MCP servers.
• Design and implement software architecture, ensuring solutions are scalable, maintainable, secure, and suitable for AI-assisted development.
• Ensure the quality of AI-generated code through TDD, automated testing, code reviews, and static and security analysis in CI/CD pipelines.
• Identify and mitigate AI agent security risks, including permissions management, secrets protection, client data confidentiality, and prompt injection.
• Optimize AI usage and development efficiency by selecting appropriate models, monitoring token consumption and premium requests, and evaluating productivity impact.
• Collaborate with clients and technical stakeholders to understand requirements, propose solutions, and contribute to technical discussions.
• Mentor less experienced engineers and share best practices in AI-native software engineering.
• Contribute to technical PoCs, solution estimates, and presales activities.

Qualifications

• 5+ years of professional software engineering experience, with hands-on expertise in Java, .NET, or Python, and strong software design and debugging skills.
• 6+ months of daily, hands-on experience using AI coding agents (GitHub Copilot agent mode / CLI / coding agent, Claude Code, or Codex) on real-world projects.
• Strong understanding of context engineering for coding agents, including repository instructions, prompt files, skills, custom agents, subagents, and MCP.
• Practical experience with spec-driven development, including breaking down complex requirements into well-defined tasks suitable for AI agents.
• Proven ability to maintain production-quality standards for AI-generated code through TDD, test automation, reviewing large AI-generated diffs, and CI/CD quality gates.
• Understanding of AI agent security risks, including permissions, secrets management, data leakage, and prompt injection through repositories and tools.
• Practical knowledge of AI cost optimization, including model selection, token and premium-request consumption, and measuring productivity impact.
• Solid software architecture and system design skills.
• Experience collaborating with clients and technical stakeholders, communicating technical decisions, and contributing to engineering best practices.
• English B2+

Nice to have

• Building LLM or agentic applications (agent frameworks, RAG, tool calling, evals, guardrails, LLM observability).
• Rolling out AI-assisted development to other teams (enablement, playbooks, metrics).
• Cloud and AI certifications (Azure, AWS, GCP, GitHub Copilot, Anthropic).
• Business analysis mindset; consulting or presales experience; UX/UI; financial services domain.