Gen AI Developer

HubSync is looking for a Generative AI Developer to be a strategic partner to product, a hands-on technical lead, and a core driver of what we build and how we build it. If you are excited about designing and deploying GenAI systems from 0 to 1, and enjoy working in a fast-paced, high-impact environment, this role is for you. 

Responsibilities 

• Partner closely with product leadership to translate early product ideas into working prototypes and then into robust, production-ready generative AI applications.   

• Design and build full-stack AI systems leveraging state-of-the-art large language models (LLMs) such as GPT-4, Claude, Mistral, LLaMA and similar, along with modern agentic frameworks (for example, LangGraph and CrewAI). 

• Own the 0-to-1 architecture for retrieval-augmented generation (RAG), agentic workflows, and document intelligence pipelines, including retrieval, orchestration, prompting, and output handling.   

• Experiment, build, and iterate rapidly, deploying MVPs to users and evolving solutions based on real-world feedback and performance data.   

• Build intelligent document processing (IDP) solutions to extract, understand, and generate insights from complex, unstructured documents.   

• Evaluate and benchmark models by testing different model providers, prompts, and configurations to optimize for quality, latency, cost, and reliability across target tasks.   

• Help shape our overall AI strategy and technology roadmap by staying current on emerging AI capabilities and identifying high-potential tools and approaches for early adoption.   

What We’re Looking For (Requirements)

• Someone collaborative and comfortable working in a fast-paced, startup-like environment with evolving priorities.   

• Hands-on experience building generative AI products that have meaningful, real user-facing impact.   

• Deep understanding of LLMs, prompt engineering, RAG techniques, and agentic workflow patterns.   

• Familiarity with tools such as LangChain, LlamaIndex, Hugging Face, and vector databases like Pinecone, Weaviate, or FAISS.   

• Experience working with LLMs via APIs (for example, OpenAI and Anthropic) and/or deploying and operating open-source models.   

• Strong software engineering best practices; you write clean, maintainable, production-grade code and are comfortable with modern development workflows.   

• Comfort working with AWS cloud infrastructure for deploying and scaling AI-powered applications.   

Bonus Qualifications 

• Experience with intelligent document processing (IDP), form understanding, or document-based retrieval systems.   

• Prior work with agentic frameworks such as LangGraph, CrewAI, or AutoGen.   

• Knowledge of NLP techniques, embeddings, and LLM evaluation metrics to systematically assess and improve model performance.   

• Background in applied ML/AI research or AI product development at an early-stage company or similar high-growth environment.