Senior Full Stack AI Engineer

Senior Full Stack AI Engineer
MERN + Generative AI | 7+ Years | Early-Stage Startup | Onsite
About the Role
We are an early-stage, AI-first startup building a product that is moving fast from early traction to scale. We are looking for a hands-on senior engineer who has built and shipped full-stack products, has led small teams, and is excited to put large language models (LLMs) and AI agents at the center of real user workflows.
This is not a maintenance role. You will help shape the architecture, own features end to end, and turn a working product into a reliable, secure, multi-tenant platform that can grow with our customers. You will work directly with the founders and have real influence over the technical direction.
What You Will DoBuild and scale the product
• Own features end to end: design, build, ship and iterate on core product features across React.js front ends and Node.js/Express.js services.
• Scale the platform: evolve the architecture from MVP to production-grade, covering multi-tenancy, performance, caching, background jobs and cost-efficient infrastructure.
• Design APIs and data models: build RESTful (and where it fits, event-driven) APIs on MongoDB and MySQL, with clean schemas that support fast product iteration.
• Raise the engineering bar: set up CI/CD, automated testing, observability and code-review practices that let a small team ship quickly without breaking things.
Build the AI layer
• Integrate LLMs into the product: build features on leading model APIs (e.g., OpenAI, Anthropic Claude, Google Gemini), including structured outputs, tool/function calling and streaming responses.
• Build RAG pipelines: implement retrieval-augmented generation with embeddings and vector search (e.g., MongoDB Atlas Vector Search, pgvector, Pinecone) so the product answers from customer data.
• Develop AI agents and workflows: design multi-step agentic workflows, conversational assistants and automations that complete real tasks for users, with clear guardrails and human-in-the-loop controls.
• Engineer prompts and evaluate quality: write, version and test prompts; build evaluation sets and monitoring to track accuracy, hallucination, latency and token cost.
• Run AI responsibly in production: handle data privacy, PII protection, rate limits, fallbacks between models and graceful failure.
• Use Python where it fits: build Python services for AI/ML pipelines, data processing and integrations alongside the Node.js core; support legacy PHP integrations where needed.
Lead and collaborate
• Mentor and lead: guide a small team of developers through code reviews, pairing and technical planning.
• Partner with product and founders: turn customer problems into technical solutions, scope MVPs and make pragmatic build-vs-buy calls.
• Work AI-native: use AI coding assistants (e.g., GitHub Copilot, Cursor, Claude Code) to move faster, and help the team adopt them well.
What You BringMust have
• 7+ years of full-stack development experience, including 3+ years leading a team or owning a product area as tech lead.
• Deep expertise in the MERN stack (MongoDB, Express.js, React.js, Node.js) and modern JavaScript/TypeScript (ES6+), HTML5, CSS3 and responsive design.
• Hands-on experience shipping at least one production feature powered by LLM APIs (chatbot, assistant, RAG search, summarization, extraction or agent).
• Working knowledge of prompt engineering, embeddings, vector databases and the RAG pattern.
• Strong Python skills for backend and AI services; PHP experience is a plus.
• Experience deploying and running applications on a major cloud (GCP preferred; AWS or Azure also welcome), with Git-based workflows.
• A track record of scaling a product: improving performance, reliability and architecture as usage grows.
• Startup mindset: comfortable with ambiguity, fast iteration and wearing multiple hats.
• Excellent communication skills and the ability to explain technical trade-offs to non-technical stakeholders.
• Bachelor's or Master's degree in Computer Science, Engineering or a related field preferred.
Nice to have
• Experience with agent and orchestration frameworks such as LangChain, LangGraph, LlamaIndex or the Model Context Protocol (MCP).
• Experience with LLM evaluation and observability tools (e.g., LangSmith, Langfuse, Promptfoo).
• Familiarity with fine-tuning, open-source models (e.g., Llama, Mistral) or model hosting.
• Voice AI, speech-to-text or real-time conversational interfaces.
• DevOps experience: Docker, Kubernetes, infrastructure as code and CI/CD pipelines.
• Experience building in regulated domains with security and compliance requirements (e.g., HIPAA, SOC 2).
• Prior experience at an early-stage startup, ideally through a scale-up phase.
Why Join Us
• Ground-floor impact: your architecture and code will become the foundation of the product.
• Build real AI products: work on applied generative AI in production, not demos.
• Ownership and growth: a clear path to grow with the company into a senior technical leadership role as the team expands.
• Small, fast team: direct access to the founders, quick decisions and little bureaucracy.

Work arrangement
No