Backend Engineer AI

Build and maintain AI-native backend services in Python that integrate LLMs, agents, and tool calls within core product workflows.

Develop evaluation and reinforcement learning loops to measure and improve model performance using techniques like RLHF and reward modeling.

Ensure scalable, reliable, end-to-end systems with attention to latency, cost, testing, monitoring, and observability.

4-6 years of backend engineering experience with hands-on building and running LLM-powered production features.

Strong proficiency in Python, including async programming and experience with frameworks like FastAPI, Django, or Flask.

Experience with LLM APIs (OpenAI, Anthropic, Gemini), prompt design, tool calling, RAG, and vector databases (pgvector, Pinecone, Weaviate or similar).

Solid knowledge of databases, distributed systems, cloud infrastructure (AWS or GCP), message queues, Docker, and Kubernetes.

Experienced building scalable backend systems that incorporate AI and LLM technologies in production environments with a focus on reliability and efficiency.

Comfortable working with evaluation tools and reinforcement learning methodologies to continuously improve AI system performance.

Familiarity with agent frameworks, fine-tuning, browser automation, or regulated domains like fintech or travel is a strong advantage.