Full Stack Engineer – AI & LLM

Requirements Must have:

• Developed production‑level AI systems (bots, RAG, agents, orchestrations)
• Familiarity with GPT‑4, Claude, Lang Chain, Llama Index, and agent frameworks
• In-depth knowledge of embeddings and vector databases
• Experience designing RAG pipelines and context architectures
• The ability to construct multi‑step agentic workflows and tool systems
• Strong foundation in prompt engineering and prompt security comprehension
• Proficiency in evaluating model performance and enhancing reliability
• Comfort with AI development tools (e.g., Cursor, Claude, Copilot)

While full‑stack ability is not the primary focus, it is essential for integrating AI features, and we require experience with Mongo

DB, Express, React, and Node.js, along with strong debugging and integration skills.

• Architect, build, and deploy cutting‑edge AI capabilities, including AI‑powered bots and conversational assistants
• Develop knowledge‑base systems (RAG, embeddings, vector databases, context management)
• Design agentic systems that utilize tools, facilitate multi‑step reasoning, and incorporate dynamic workflows
• Create fine‑tuned prompts, implement guardrails, and conduct output evaluations
• Select models, tune performance, and optimize costs
• Integrate AI features into our existing MERN‑based platform

If your enthusiasm lies in constructing genuine AI systems, rather than mere prototypes, this role has been tailor‑made for you.

To apply, please adhere strictly to the following steps, as skipping any will result in an automatic decline:

This is a full‑time role with a salary ranging from $80,000 to $90,000 per year. Benefits include health insurance and relocation assistance. This position is in‑person.