AI Engineer

About the Role
Join a dynamic engineering team dedicated to constructing agentic AI architecture that leverages large language models to manage planning, execution, and tool interactions with minimal supervision. This hands-on backend software engineering position primarily involves coding, testing, and conducting system diagnostics while addressing complex architectural challenges. You will have the opportunity to work across diverse seniority levels, with production-grade agentic engineering being an emerging field. Our team values engineering excellence, ensuring that junior engineers work closely with seasoned mentors to take ownership of production components within three months, while senior engineers lead in setting technical standards and driving architectural vision.

What You Will Do

• Architect and maintain agent infrastructure, including orchestration logic, session handling, state management, and reliable backend service interfaces.
• Design robust tool integrations and MCP servers with clear boundary definitions and comprehensive error recovery mechanisms.
• Implement end-to-end tracing and observability for model calls, retrieval, and tool executions in line with OpenTelemetry GenAI standards.
• Develop evaluation suites, benchmarks, and regression tests to validate model iterations and systematically capture production edge cases.
• Execute in-depth root cause analysis on runtime failures, loops, context degradation, or hallucinated outputs to enhance system resiliency.
• Institute runtime guardrails, cost thresholds, RBAC permissions, output validation schemas, and human-in-the-loop validation triggers.
• Stay informed of industry advancements, emerging AI research, and architectural trends, sharing technical insights across the engineering organization.

What Are We Looking For
Essential

• Deep software engineering expertise in a modern programming language, emphasizing algorithmic depth rather than superficial multi-language experience.
• Strong foundational skills in computer science, including data structures, algorithms, memory allocation, and concurrent execution patterns.
• Practical experience with backend infrastructure: REST/gRPC APIs, relational/non-relational databases, caching tiers, message queues, and distributed systems resilience.
• Proficient with Git, automated testing frameworks, CI/CD pipelines, and writing clean, maintainable software.
• Comprehensive understanding of LLM mechanics: context window constraints, tokenization, function calling protocols, non-deterministic behaviors, and hallucination management.
• Proven history of delivering full-lifecycle technical projects in production, academia, open source, or personal projects.
• Methodical debugging skills and the ability to articulate systematic troubleshooting approaches.
• Strong technical documentation and written communication skills for conveying complex distributed system behaviors.

Expectations by Seniority Level

• Early Career: Focus on fundamental technical competencies, algorithmic problem-solving, and curiosity; mentorship provided.
• Mid-Level: Own sub-systems end-to-end, defining architecture from ambiguous requirements and demonstrating success in shipping and maintaining production services.
• Senior Level: Drive architectural strategy, possess substantial experience scaling non-deterministic systems, enhance engineering practices, and actively question technical assumptions.

Nice to Have

• Hands-on experience developing application prototypes integrated with LLM APIs.
• Familiarity with Model Context Protocol (MCP) or custom tool integrations.
• Understanding of vector database indexing, embedding generation, and retrieval pipelines (RAG).
• Experience with cloud infrastructures (AWS preferred), containerization (Docker/Kubernetes), telemetry, or IaC tooling.
• Knowledge of GenAI security paradigms, prompt injection mitigation, and threat modeling.
• Active involvement in open-source contributions or community participation.

Out of Scope

• Extensive experience with specific agent frameworks due to the nascent state of the ecosystem.
• Academic AI research background, specialized ML qualifications, or mathematical derivation of backpropagation.
• Profound expertise in base model training or fine-tuning workflows.
• Flawless portfolio presentations, with significance placed on technical depth and problem-solving skills.
• Strict career trajectories; diverse and self-taught engineering backgrounds are equally considered.

Technical Standards & Architecture

• The engineering ecosystem adheres to industry standards, with continuous learning embedded in onboarding processes.
• Model Context Protocol (MCP): An open standard promoting model integration with tool services and data stores.
• OpenTelemetry GenAI Conventions: Standardized schemas for tracking model execution traces, step transitions, and tool invocations.
• OWASP GenAI & Agentic Security Guidelines: Threat modeling standards focusing on containment strategies and authorization safeguards.
• Eval-Driven Development: Requires thorough evaluation validation before implementing behavioral changes, relying on internal test harnesses.

What We Offer You

• An inclusive and diverse culture that fosters innovation and flexible work environments, including in-office and hybrid setups.
• Highly competitive compensation packages, including bonuses and opportunities for equity.
• Commitment to personal development with regular training and an annual learning stipend to embrace new challenges within a hyper-growth environment.
• Collaboration with a talented team representing over 30 nationalities across 14 countries, providing valuable industry experience.
• Autonomy, mentorship, and ambitious goals that create exceptional opportunities for personal and professional growth.