About the job
Pulsora, the “Enterprise Sustainability Platform,” is seeking a highly skilled and experienced engineer to independently build and scale full-stack products, while also designing and deploying reliable LLM-powered systems and agent workflows in production.
What you will do
- 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 to production to iteration across backend and frontend.
- Build scalable, maintainable systems that solve real customer problems.
- Design & Operate GenAI Systems
- Develop prompt strategies, context management (RAG, memory), and agent workflows.
- Integrate and optimize across leading LLM APIs (OpenAI, Anthropic, Gemini, open-source).
- Continuously improve system quality, reliability, and performance.
- Leverage AI-First Development Workflows
- Use AI-assisted coding tools (e.g., Cursor, Copilot, Claude Code) to accelerate development.
- Validate, test, and safely integrate AI-generated code into production systems.
- Contribute to evolving best practices for AI-first engineering.
- Ensure Quality, Reliability & Performance
- Own testing strategy including unit, integration, and end-to-end testing.
- Define and implement evaluation frameworks for AI outputs (quality, consistency, failure modes).
- 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 (this will require the willingness to work overlapping with US working hours).
- Advance AI & Product Capabilities (Nice to Have Contributions)
- 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.
About you
- Bachelor’s degree in Computer Science, Engineering, or a 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 use), and multi-step/agentic workflows.
- Ability to take products from concept to production and iteration across backend and frontend systems, including working across the full engineering lifecycle.
- Practical experience using tools like Claude Code, Cursor, OpenAI, Microsoft Copilot, including the ability to safely integrate AI-generated code into production (validation, CI/CD).
- Experience debugging production issues, optimizing performance (latency, cost), and building maintainable systems.
- Ability to define evaluation strategies for AI outputs (quality, consistency, failure modes) and experience with AI-driven testing and reliability practices.
A little more about how you like to work
- Strong collaboration across a small team, including great communication with both onshore and offshore departments and translating vague requirements into actionable systems.
- Self-motivated and proactive—you create momentum without needing direction.
- A strong problem solver who can navigate ambiguity.
- A builder who cares about shipping real, working products.
- Comfortable with ownership, accountability, and high expectations.
- Thrives outside of traditional work structures.
- You own the quality of the product you build.