You will join a team whose mission is AI Developer Experience (DX): building the context, tools, knowledge bases, and guidance that help QIMA’s software engineering organisation work in an AI-first way. This role is not centred on shipping product features for end users; it is centred on making every engineer more effective, safe, and aligned with how we build at scale.
Our vision for software engineering. We expect AI agents to take on an increasing share of implementation work—coding, integration, and quality assurance—while engineers remain accountable for review, release, and production outcomes, and concentrate on what creates lasting business value: identifying the next capabilities to deliver, defining sound architecture, managing technical debt, and excelling in data stewardship and security across the stack. To turn that vision into reality, we are investing in the environment, standards, and platforms that support it.
In this role you will be part of the engineering team, working with product, internal platform owners, and security stakeholders to design that environment—so agent-assisted work stays auditable, compliant, and grounded in QIMA’s architecture and domain knowledge.
Job Responsibilities
Effective delivery—with AI-assisted engineering as the default way we build—depends on the environment, standards, and platforms this role builds and evolves with engineering leadership. You will be expected to:
Define and evolve engineering context for AI-first delivery—architecture principles, patterns, guardrails, and playbooks that teams and agents can follow.
Build and curate knowledge bases and retrieval pipelines (documentation, APIs, runbooks, domain context) so agents and engineers share a trustworthy source of truth.
Create and maintain developer tools and integrations (e.g. MCP services, GitHub, Jira, CircleCI, and knowledge sources) that connect agents to our engineering workflow safely.
Design guidance for AI-assisted engineering—versioned Skills, rules, templates, and examples in tools such as Cursor, Claude Code, and comparable IDEs—and help teams adopt them consistently.
Evaluate emerging AI tools, models, and practices; run practical trials and recommend what engineering teams should adopt at QIMA, with clear rationale and guardrails.
Be part of the engineering team to improve developer experience: onboarding, feedback loops, metrics, and continuous refinement of the AI-first environment. Validate context, tools, and guidance against real delivery codebases (e.g. Java / Spring and current frontends), not demos only.
Champion data and security boundaries for agent access—credentials, permissions, logging, and compliance with QIMA quality and security standards.
Your profile
It could be you if you have:
Fluent English (written and spoken) is mandatory for documentation, standards, and collaboration with global engineering and leadership;
Bachelor’s degree in Computer Science or Software Engineering, or equivalent experience;
3+ years in software engineering with hands-on experience in enterprise systems (e.g. Java / microservices and modern web stacks) so you understand what delivery teams need;
Proficiency in at least one scripting or automation language (e.g. Python or TypeScript) for retrieval pipelines, integrations, and internal tooling;
Sound judgment on architecture, technical debt, and production quality; comfort discussing data handling and security with engineering and security partners;
Practical experience with LLMs, AI agents, tool calling, and RAG; daily use of AI-assisted coding tools in development workflows;
Curiosity about AI—you stay current with developments, experiment thoughtfully, and assess what is worth adopting for QIMA;
Daily use of Git, code review, and CI/CD; familiarity with Jira or similar planning tools.
Preferred qualifications:
Prior Developer Experience or platform engineering experience;
MCP Server development or deep integration experience;
Solid experience with relational databases (e.g. Oracle, PostgreSQL) and SQL;
Practical experience with AWS (or Aliyun, GCP) in development and integration;
Hands-on experience with vector databases and multi-agent orchestration;
This is an engineering role that builds the AI-first developer environment—not algorithm research, not prompt-only, and not a feature-factory IC.