Senior Backend Engineer
Posted Updated
Description
We are looking for a Senior Backend Engineer who builds fast, reliable systems and treats AI as a first-class engineering tool, not a buzzword. You will design and ship production-grade backend services in Node.js, and integrate modern AI capabilities (LLMs, RAG, agents, embeddings) into real product workflows. This is a hands-on role for someone who writes clean code, owns systems end-to-end, and uses AI to move faster without compromising quality.
Responsibilities:
- Design, build, and scale backend services and REST/GraphQL APIs using Node.js (Express / NestJS / Fastify).
- Integrate LLM-powered features into products, RAG pipelines, semantic search, chat/agent workflows, and structured AI outputs.
- Work with vector databases (pgvector, Pinecone, Weaviate, Qdrant) and embedding models for retrieval and recommendation.
- Architect data layers across PostgreSQL, Redis, and NoSQL stores, with a focus on performance and low latency.
- Build and consume APIs from AI providers (OpenAI, Anthropic, Bedrock, etc. ) with proper cost, latency, and reliability controls.
- Use AI-assisted development tools (Copilot, Claude, Cursor) to ship higher-quality code faster.
- Write tests, set up CI/CD, and own services in production monitoring, logging, and incident response, including.
- Collaborate with product, frontend, and data teams to turn requirements into well-architected systems.
Requirements:
- Must-have items are required from day one.
- Required items are expected within your first month. Optional items are a strong plus.
- 4-5 years of professional backend development experience, primarily in Node.js / TypeScript.
- Strong grasp of JavaScript/TypeScript fundamentals, async patterns, and event-driven architecture.
- Solid experience designing and scaling RESTful and/or GraphQL APIs.
- Proven experience with relational and NoSQL databases (PostgreSQL, MongoDB) and caching with Redis.
- Hands-on experience integrating at least one LLM/AI API into a real product or feature.
- Comfortable with Docker, Git, and CI/CD pipelines.
- Understanding of system design, scalability, and security best practices.
AI-Native Skills (Strongly Preferred):
- Practical experience building RAG pipelines or retrieval systems with vector databases.
- Familiarity with prompt engineering, function/tool calling, and structuring reliable LLM outputs.
- Experience with AI frameworks such as LangChain, LlamaIndex, or the Vercel AI SDK.
- Awareness of LLM cost optimisation, token management, streaming, and evaluation/guardrails.
- Daily use of AI coding assistants as part of a real engineering workflow.
Skills
Sign in to read and join the discussion.