AI Engineer

About the role

You will construct agentic AI architecture, leveraging large language models to orchestrate planning, execution, and tool interactions with minimal supervision. Working within a compact engineering team, you will build the core foundational infrastructure, spanning microservices, integration protocols, state management, tracing, and evaluation harnesses, ensuring systems are production‑ready, reliable, and scalable.

Key responsibilities

• Architect and maintain agent infrastructure, including orchestration logic, session handling, state management, and reliable backend service interfaces.
• Design robust tool integrations and Model Context Protocol (MCP) servers with precise boundary definitions and comprehensive error‑recovery handlers.
• Implement end‑to‑end tracing and observability for model calls, retrieval, and tool executions following OpenTelemetry GenAI standards.
• Construct evaluation suites, benchmarks, and regression tests to validate model iterations and capture production edge cases.
• Perform deep‑dive root‑cause analysis on runtime failures, loops, context degradation, or hallucinated outputs to improve system resiliency.
• Enforce runtime guardrails, cost thresholds, RBAC permissions, output validation schemas, and human‑in‑the‑loop validation triggers.
• Monitor emerging AI research and architectural patterns, sharing technical insights across the engineering organization.

Required profile

• Deep software engineering expertise in a modern programming language with strong algorithmic depth.
• Solid computer‑science foundations in data structures, algorithms, memory allocation, and concurrent execution patterns.
• Practical experience with backend infrastructure: REST/gRPC APIs, relational and non‑relational databases, caching tiers, message queues, and distributed‑system resilience.
• Proficiency with Git, automated testing frameworks, CI/CD pipelines, and clean, maintainable code.
• Comprehensive mental model of LLM mechanics, including context windows, tokenization, function‑calling protocols, non‑deterministic behavior, and hallucination management.
• Proven track record delivering full‑lifecycle technical projects in production, open‑source, or side initiatives.
• Methodical debugging skills and strong technical documentation abilities.

Required skills

• REST/gRPC APIs
• Relational and non‑relational databases
• Caching systems
• Message queues
• Distributed systems
• Git
• Automated testing frameworks
• CI/CD pipelines
• OpenTelemetry
• Model Context Protocol (MCP)
• Vector database indexing, embedding generation, and retrieval pipelines (RAG)
• AWS cloud services
• Docker
• Kubernetes
• Infrastructure‑as‑Code tooling
• GenAI security practices (prompt‑injection mitigation)

What we offer

• Inclusive, diverse culture encouraging innovation and hybrid work setups.
• Highly competitive compensation packages, bonuses and potential equity.
• Personal development through regular training and an annual learning stipend.
• Opportunity to work with a multinational team across 14 countries.
• Autonomy, mentoring and challenging goals for rapid career growth.