Pulsora, a well-funded Silicon Valley sustainability platform startup, is seeking a skilled engineer to build and scale full-stack AI products. The role involves designing and deploying LLM-powered systems and agent workflows in production, with a focus on prompt strategies, RAG, and agent orchestration. You will work with leading LLM APIs and AI-assisted coding tools to accelerate development.
Responsibilities
Build & Ship AI-Powered Products: Design, develop, and deploy LLM-powered applications and agent-based systems in production
Own the full product lifecycle from concept → production → iteration across backend and frontend
Build scalable, maintainable systems that solve real customer problems
Hirevector is a professional services and recruitment firm that provides an AI-powered technical interview intelligence platform. The company focuses on standardizing the hiring process through conversational, AI-driven assessments to ensure fairness, reduce bias, and improve candidate evaluation.
Debug production issues and optimize for latency, cost, and scalability
Take full ownership of system reliability and production stability
Collaborate & Execute in Fast-Moving Environments: Translate ambiguous requirements into working solutions
Partner with product, design, and customer-facing teams to deliver impactful features
Collaborate effectively with distributed and offshore engineering teams
Requirements
Bachelor’s degree in Computer Science, Engineering, or related field preferred (or equivalent hands-on experience)
1-2 years of experience building AI-powered applications (AI agents or AI-assisted coding) and building and deploying LLM-powered applications or agents in production
Experience integrating major LLM APIs (e.g., OpenAI, Anthropic, Gemini, open-source)
Working knowledge of prompt design, context management (RAG, memory, tool)
Nice to Have
Build advanced agent systems (planning, orchestration, parallel execution)
Apply frameworks like LangChain, LangGraph, or similar where appropriate
Explore fine-tuning, evaluation frameworks, and benchmarking techniques
Contribute to intuitive, user-friendly AI-driven experiences and human-in-the-loop workflows