Middle AI Agent Engineer

Langate is an award-winning provider of web development services in 3 main categories: business, healthcare, and education. At Langate, we're passionate about crafting digital solutions that make a real impact. We take immense pride in our strong collaboration with the U.S.  We're here to shape the future of technology, one milestone at a time. 
In addition to technical expertise, we value strong communication, autonomy, and a high level of business orientation. This role requires close collaboration with stakeholders, proactive requirement discovery, and the ability to work effectively in a fast-changing environment without waiting for fully documented inputs. 
To thrive in this role, we’re seeking candidates with 2–3+ years of commercial engineering experience, hands-on experience building AI agent solutions, strong Python and/or TypeScript fundamentals, and the ability to design custom tool-using agent loops from scratch. Experience with agent frameworks, evaluation systems, and observability tooling will be a strong advantage. 

About the project : The project is focused on building production-grade AI agent capabilities for the U.S. healthcare domain. The engineer will work on agentic product features, legacy-system integrations, and supporting components such as scrapers and tool layers, helping automate complex workflows in an environment with significant real-world business impact. 

Requirements:  

• 2–3+ years of commercial engineering experience
• Ability to build a tool-using agent loop from scratch, including tool calling, structured outputs, stop reasons, parallel tool use, and error recovery
• Strong understanding of context engineering, including what to write, select, compress, and isolate
• Hands-on experience with modern agent frameworks or SDKs such as LangGraph, Claude Agent SDK, OpenAI Agents SDK, or Pydantic AI
• Working knowledge of Model Context Protocol (MCP)
• Experience building or extending evaluation harnesses, solid Python and/or TypeScript skills, and Upper-Intermediate English 

Responsibilities: 

• Design and implement agentic features end-to-end, from prototype to production.
• Build and maintain agent loops, tool layers, context management, persistence, sub-agent orchestration, observability, and safety hooks.
• Define quality standards for agent performance by creating golden datasets, writing evaluations, and setting up regression checks.
• Instrument agents with proper tracing and telemetry, and investigate production behavior using real execution traces.
• Work directly with client stakeholders to elicit and refine requirements, translate them into technical scope, and align on expected outcomes.
• Make pragmatic build-versus-import decisions when selecting frameworks, tools, and external components.
• Participate in architecture discussions and code reviews, contributing to scalable and production-ready engineering decisions.
• Move between projects and priorities as needed, taking ownership of delivery in a fast-changing environment with a high degree of autonomy. 

Schedule: 5/2, 8-hour working day (40 hr per week), flexible schedule. 

Hiring process: HR interview + tech specialists