About the role
We are hiring Backend Engineers who enjoy building production-grade AI-powered systems at scale. This role is focused on designing and shipping backend infrastructure powering intelligent workflows, recommendation systems, semantic retrieval, and large-scale AI applications. This is not a research-only role. We are looking for strong engineers who can own systems end-to-end from architecture and APIs to deployment, reliability, observability, and scaling.
Responsibilities:
- AI-powered backend systems for recommendation and personalization.
- Retrieval-Augmented Generation (RAG) pipelines.
- Content ingestion, embeddings, semantic search, and ranking systems.
- High-performance APIs and backend services.
- Scalable AI workflows with strong observability and monitoring.
- Cost and latency-optimized AI infrastructure.
- Design and build scalable backend systems using Python.
- Develop APIs, AI pipelines, and distributed systems.
- Translate product ideas into production-grade systems.
- Optimize performance, deployment, monitoring, and reliability.
- Own systems from development to production and iteration.
Requirements:
- 5-10 years of strong backend engineering experience.
- Strong hands-on expertise in Python.
- Experience with FastAPI / Flask and backend architecture.
- Strong understanding of APIs, debugging, scalable systems, and system design.
- Hands-on exposure to Docker and deployment workflows.
- Practical exposure to LLM ecosystems, RAG systems, AI tooling, or semantic search.
- Experience with OpenAI SDK, LangChain, Haystack, or similar frameworks preferred.
- Strong computer science fundamentals and problem-solving mindset.
Preferred Background:
- Engineers from strong startup or product-based environments.
- Candidates from top engineering institutes or exceptional OSS/project backgrounds.
- Builders who enjoy ownership, speed, ambiguity, and execution.