Senior Engineer (AI-Assisted Development)

What You'll Do

• Work in hybrid engineering teams where humans and AI agents collaborate as part of the same delivery workflow
• Stay in the loop for key responsibilities:
• Setting direction and technical strategy
• Quality assurance and validation of AI-assisted outputs
• Critical decision-making and maintaining accountability for outcomes
• Managing client relationships and translating business needs into solutions
• Guide implementation by combining hands-on development with AI-assisted execution
• Break down complex problems into structured tasks that can be executed by the hybrid team
• Contribute to defining best practices and workflows for effective human + AI collaboration
• Identify opportunities where AI can accelerate delivery while ensuring human expertise drives reliability
  

Flexible schedule, international projects, home office kit, healthcare and more, you name it. Check out the whole list of benefits on our dedicated page, by clicking the following link: Benefits

Must Have

• Hands-on experience with Java / .NET / Frontend frameworks

AI-Augmented Development Tools

Coding assistants & agentic IDEs

• GitHub Copilot (inline completion + Copilot Chat / Copilot Agent mode)
• Cursor IDE — agentic, multi-file editing with natural language instructions
• Windsurf (Codeium) — agentic coding with Cascade
• JetBrains AI Assistant — relevant for Java/.NET leads already on IntelliJ/Rider
• Continue.dev — open-source, self-hosted alternative (relevant for security-conscious clients)

• Claude Code — terminal-based agentic coding
• Kilo Code — VS Code extension for agentic, multi-step coding tasks; open-source fork of Cline with strong local model support
• OpenCode — terminal-native AI coding agent, model-agnostic; relevant for engineers who prefer CLI-first workflows or self-hosted setups
• GitHub Copilot Agent mode
• Devin, SWE-agent (awareness-level)

• Prompt engineering for code generation — writing effective, context-rich prompts; iterating on AI output rather than accepting it blindly
• AI-assisted code review — using LLM tools to pre-screen PRs, catch patterns, suggest refactors
• Test generation with AI — leveraging Copilot/Cursor to scaffold unit and integration tests
• Context engineering — structuring repos, READMEs, and architecture docs so AI tools can reason over them effectively (this is the senior/lead differentiator)
• Agentic workflow design — ability to break tasks into agent-executable steps; understanding when to use human-in-the-loop vs. autonomous execution

• OpenAI API / Azure OpenAI
• Anthropic API (Claude)
• AWS Bedrock or Google Vertex AI (for DevOps/cloud leads)
• LangChain or LlamaIndex — basic understanding of RAG and chain patterns

• AI-assisted IaC generation (Copilot + Terraform, Pulumi AI)
• GitHub Actions with AI steps or LLM-based pipeline stages
• Monitoring/observability tools with AI anomaly detection (Datadog AI, AWS DevOps Guru)