About the JobCompany: Markitech
Type: Full-Time
About the Role:Markitech is looking for a hands-on Solutions Architect / Prompt Engineer to join our growing AI team. In this role, you will design intelligent AI-driven solutions and use agentic AI coding platforms - such as Cursor, Claude Code, and OpenAI Codex - to generate, scaffold, and ship production-quality code. You understand how to get the most out of these tools because you have real development experience and know what good code looks like. This is not a theoretical role: you own architecture decisions and end-to-end delivery.
What You'll Do:- Use AI-powered coding platforms (Cursor, Claude Code, GitHub Copilot, OpenAI Codex, and similar) to rapidly design, generate, and iterate on software solutions.
- Architect agentic AI workflows and multi-step pipelines, then drive them to working implementations using AI-assisted development tools.
- Engineer, optimize, and evaluate prompts - including system prompts, chain-of-thought strategies, tool/function calling, and structured outputs - to get reliable, high-quality results from LLMs.
- Review and own AI-generated code: validate correctness, refactor for production standards, and debug when things go wrong.
- Translate business and client requirements into clear technical architectures and implementation plans.
- Collaborate with stakeholders to scope AI solutions and communicate tradeoffs in plain language.
- Build evaluation frameworks and testing strategies to ensure AI outputs are reliable and safe.
- Stay ahead of the curve on emerging AI coding tools and bring best practices into the team.
What We're Looking For:- 3+ years of software development experience - you must be able to write, read, debug, and review code independently (Python strongly preferred; JavaScript/TypeScript a plus).
- Hands-on experience with AI-assisted coding platforms such as Cursor, Claude Code, OpenAI Codex, GitHub Copilot, or equivalent.
- Strong prompt engineering skills: you know how to craft prompts that produce consistent, production-ready outputs across code generation, reasoning, and agentic tasks.
- Ability to critically evaluate AI-generated code - catching errors, security issues, and suboptimal patterns before they reach production.
- Experience working with LLM APIs (OpenAI, Anthropic, Azure OpenAI, Gemini, etc.) and integrating them into real applications.
- Solid understanding of software architecture principles - APIs, microservices, data pipelines, and deployment patterns.
- Strong communication skills - able to present solutions and tradeoffs to both technical teams and non-technical stakeholders.
Nice to Have:- Experience with agentic frameworks such as LangChain, LangGraph, AutoGen, or CrewAI.
- Familiarity with RAG patterns and vector databases (Pinecone, pgvector, Chroma, etc.).
- Cloud platform experience (AWS, Azure, GCP) and containerized deployments (Docker, Kubernetes).
- Background in a consulting or client-facing solutions role.
- Exposure to AI evaluation tooling (LangSmith, PromptFlow, RAGAS, etc.).
