SE2 AI Engineer
Core
Design and implement intelligent agents and assistants that provide contextualized, personalized, and scalable responses for business needs.
Role type
Senior IC Generative AI Engineer (LLM Agents & RAG)
Builds
Scalable AI solutions, intelligent agents, and backend services for enterprise clients
Domain
Generative AI, Large Language Models (LLMs), and Enterprise Software
Deliverable
production ML models | product features
Required skills
Generative AI, LLMs, LangChain, RAG, Python, REST APIs, Vector Databases, LLMOps, Prompt Engineering, Context Engineering, Foundation Models, Tool Calling, Function Calling, MCP, Prompt Chaining, Structured Outputs, Human-in-the-Loop evaluation, Clean Code, SOLID principles, Git, Relational and NoSQL databases
Preferred skills
Docker, Kubernetes, CI/CD, Cloud platforms (Vertex AI, AWS, Azure, GCP), Agile methodologies (Scrum, Kanban), External API integration, AI security and governance
Technologies
LangChain, Google ADK, Vercel AI SDK, Python, TypeScript, REST, Git, Vector Databases, Foundation Models
Responsibilities
Design and implement intelligent agents and assistants; Analyze business requirements to define appropriate GenAI solutions; Design scalable AI architectures considering performance, maintainability, security, and costs; Implement RAG architectures integrated with vector databases; Develop backend APIs and services to expose AI capabilities; Deploy, monitor, and optimize solutions in production environments; Continuously evaluate agent performance using objective metrics and Human-in-the-Loop mechanisms; Optimize prompts, context retrieval strategies, memory, and conversational flows; Document technical architectures and decisions; Collaborate with multidisciplinary teams to transform business needs into robust AI solutions
Seniority
Mid-level, hands-on IC