Senior/Lead AI engineer

Quick Facts

• Role: Senior / Lead AI Software Engineer
• Focus: Production-grade, LLM-powered applications for AI coding agents (meta-prompting, context engineering, centralized knowledge management)

Description

You will build and implement production-grade, LLM-powered services that provide structured context—rules, skills, workflows, sub-agents—to guide AI systems with deep understanding of system architecture, domain constraints, and engineering standards. As a technical lead, you will deliver developer-facing AI infrastructure, build advanced RAG pipelines, accelerate onboarding by reverse-engineering architecture and domain context, and mentor mid-level developers.

Responsibilities

• Design, build, and deploy production-grade LLM-powered services, microservices, and APIs using Python and TypeScript.
• Implement advanced meta-prompting frameworks controlling and guiding models through formalized languages, plus prompt optimization techniques for deterministic, context-aware outputs.
• Develop scalable Retrieval-Augmented Generation (RAG) pipelines and integrate vector databases (Pinecone, Weaviate, or ChromaDB) for deep context engineering and semantic code search.
• Orchestrate LLM workflows using LangChain or LlamaIndex to connect multi-agent tools, system constraints, and domain knowledge bases.
• Implement automated testing, LLM evaluation, and quality assurance frameworks to benchmark performance, accuracy, and output consistency.
• Build containerized microservices and automated CI/CD pipelines using Docker.
• Act as a hands-on Senior Developer and Mentor: guide mid-level engineers, establish coding standards, and conduct thorough code reviews.

Requirements

• 5+ years of commercial software development experience with production-grade code in Python and TypeScript.
• Strong hands-on experience integrating major LLM APIs (OpenAI, Anthropic Claude) into production software.
• Deep expertise in meta-prompting (model control via formalized languages), advanced prompt engineering, and context window optimization.
• Practical experience building and deploying RAG systems with vector databases (Pinecone, Weaviate, ChromaDB).
• Solid hands-on experience with LLM orchestration frameworks (LangChain, LlamaIndex, or similar) and embedding models.
• Demonstrated experience developing automated testing, evaluation, and observability pipelines for AI/LLM applications.
• Strong proficiency with Docker, API design, and CI/CD automation.
• Experience as a Senior/Lead Developer or Technical Mentor in a fast-paced R&D environment.
• Excellent problem-solving skills, software engineering discipline, and written/verbal English communication.

Benefits

• Opportunity to work on bleeding-edge projects
• Competitive salary
• Flexible schedule
• Benefits package (medical insurance, sports)
• Corporate social events
• Professional development opportunities
• Well-equipped office