Backend + AI Engineer

We are looking for a Backend and AI Engineer who enjoys building things from the ground up and is excited about the intersection of backend systems, AI, LLMs, and agentic applications. You will work on challenging problems involving AI-powered workflows, context-aware systems, intelligent agents, and the infrastructure required to make these systems reliable and scalable. This role is ideal for someone who is not just interested in experimenting with AI but has actually used AI to build and ship real products or meaningful systems.

Responsibilities:

• Design and build scalable backend systems and APIs for AI-native products.
• Build AI-powered workflows using LLMs, agents, RAG, tool calling, and context-aware systems.
• Design and implement agentic systems that can reason, plan, use tools, and execute tasks.
• Integrate and work with modern LLM APIs and AI frameworks.
• Build systems for context management, memory, evaluation, observability, and reliability of AI applications.
• Develop backend services that are robust, secure, maintainable, and production-ready.
• Work closely with founders and product teams to convert ambiguous problems into working products.
• Prototype quickly, test ideas, learn from failures, and iterate rapidly.
• Identify limitations and failure modes of current AI systems and build solutions around them.
• Make thoughtful engineering trade-offs between speed, scalability, reliability, and product quality.
• Contribute across the stack when required to take an idea from prototype to production.

Requirements:

• 3-8 years of experience in backend engineering, AI engineering, or a combination of both.
• Strong programming skills in Python or another modern backend language.
• Strong understanding of backend architecture, APIs, databases, distributed systems, and system design.
• Hands-on experience building applications using LLMs / generative AI.
• Experience with one or more of the following: LLM APIs, RAG, AI agents/agentic workflows, function/tool calling, vector databases, prompt engineering, AI evaluation, context/memory systems, and LangChain/LangGraph or similar frameworks.
• Experience building and deploying production-grade AI applications.
• Strong understanding of APIs, asynchronous processing, queues, databases, and cloud infrastructure.
• Ability to work independently in an early-stage, ambiguous environment.
• Strong problem-solving skills and a willingness to go deep into unfamiliar problems.
• A strong bias toward building and shipping, rather than only discussing ideas.