Description

You will build agentic systems, architect RAG pipelines, and optimize LLM performance for production AI products.

This role is on-site.

Responsibilities

• Implement multi-step workflows leveraging reasoning, self-reflection, and adaptive execution strategies.
• Design retrieval-augmented generation (RAG) and memory-augmented architectures.
• Refine prompts, experiment with few-shot learning, and utilize fine-tuned models to maximize accuracy and efficiency.
• Develop model evaluation frameworks to guarantee the accuracy and safety of AI-driven products.
• Collaborate across cross-functional teams to translate vision into end-to-end production features.

Required Skills

• 5+ years of professional software engineering experience.
• 2+ years of hands-on experience building and deploying LLM-powered applications.
• Expert-level proficiency in JavaScript and TypeScript.
• Proven experience building with LLMs, prompt chaining, and feedback loops.
• Hands-on experience with LangChain, LangGraph, and/or LlamaIndex.
• Deep understanding of software stacks, database modeling, CI/CD, and service-oriented architectures.
• Familiarity with multi-modal models (vision + text).
• Knowledge of Python.
• Experience with AWS or Azure.

Preferred Skills

• 7+ years of overall engineering experience.
• Experience with Playwright or deep knowledge of Machine Learning algorithms.

Key Skills

Education

Any Graduate