Senior Python Back-End Engineer with Gen AI experience

We’re looking for a backend-focused software engineer with a strong interest in applied AI to help us integrate LLMs, RAG pipelines, and agentic workflows into our SaaS products. This role is not about building models from scratch - it’s about engineering production-grade systems that harness existing AI models and frameworks to deliver real product value.

You’ll collaborate with product managers, LLM specialists, and domain experts to design, build, and scale intelligent features powered by modern AI technologies.

Responsibilities:

• Design and implement backend services that integrate LLM APIs (e.g., OpenAI, Claude) and retrieval-augmented generation (RAG) architectures
• Build and maintain prompt orchestration logic, agent frameworks, and tool integrations
• Work with vector databases (e.g., Pinecone, Weaviate, pgvector) to enable semantic search and retrieval
• Collaborate with product and validation teams to ensure outputs are reliable, safe, and aligned with domain expectations
• Implement monitoring, observability, and fallbacks for AI-driven services in production
• Contribute to internal SDKs, templates, and documentation for reusability across product teams

Requirements:

• 4 - 5+ years of experience as a backend or platform engineer
• Strong skills in Python, TypeScript/Node.js, or similar backend stack
• Hands-on experience with AI/LLM APIs, RAG frameworks (LangChain, LlamaIndex), or vector stores
• Understanding of prompt engineering, agent design, or AI system patterns
• Comfort working with non-deterministic systems and building safeguards around them
• Strong software engineering fundamentals: clean architecture, testing, CI/CD, logging

Nice to Have:

• Experience with agentic AI tools (LangGraph, CrewAI, etc.)
• Familiarity with LLM evaluation techniques or AI observability platforms
• Exposure to regulated environments (e.g., clinical, financial, legal tech)