Mission
Design and build production-grade, task-specific workflows that bring measurable value to enterprise users. Your work will be at the heart of Korefocus’s differentiation — bringing best-in-class AI solutions into day-to-day business processes for our clients.
You will actively shape the solution architecture, evaluate and implement the right tools and protocols, lead customization and model fine-tuning when needed, and ensure seamless integration into each client's tech stack. Your responsibility doesn’t stop at launch — you'll help iterate and optimize agents post-deployment based on usage and feedback.
Key Responsibilities
- Develop, test, and deploy custom AI agents using frameworks such as LangChain , CrewAI , or AutoGen
- Integrate agents with APIs, vector databases, and enterprise platforms (e.g., major CRM / ERP on the market, internal SaaS tools...)
- Translate complex business processes into modular, adaptable agent workflows
- Contribute to architectural decisions around agent orchestration, tool selection, and data integration
- Collaborate closely with Tech Leads to ensure performance, scalability, and security
- Work hand-in-hand with AI Transformation Consultants to iterate on agent behavior and enhance real-world value
- Stay up to date with best practices in prompt engineering , tool / function calling , memory and context management , and evaluation / feedback loops
Requirements
2–5 years of experience in software engineering, backend development, or AI applicationsHands-on experience with at least one agent framework (LangChain, CrewAI, AutoGen, etc.)Strong skills in Python and REST API integrationWorking knowledge of Model Context Protocol (MCP) — able to design and manage context flows, memory strategies, and interaction states to ensure reliable and interpretable AI behaviorExperience with vector databases , retrieval-augmented generation (RAG) architectures, and context-aware promptingUnderstanding of business processes in CRM, customer support, or pharma sales enablementBonus : Familiarity with agent UX interfaces (e.g., chat surfaces or dashboards), or experience with evaluation frameworks and agent debuggersBenefits
To be discussed