Generative AI Developer/Engineer

Job Title : Generative AI Developer/Engineer

Location : New York City, NY (Hybrid)

Job type : Contract (W2)

No Sponsorship

Interview Mode – Final round is In -Person

Experience :8 + Years

About the Role

We are seeking a Generative AI Developer/Engineer software engineering experience to build production-ready AI solutions using Python, LLMs, and Retrieval-Augmented Generation (RAG). You will design scalable systems that improve automation, search, and decision-making.

Key Responsibilities

• Develop LLM-powered applications, chatbots, and intelligent assistants using Python.
• Build RAG pipelines, including document ingestion, chunking, embeddings, retrieval, and response generation.
• Integrate OpenAI, Azure OpenAI, Anthropic, or open-source models.
• Develop APIs with FastAPI and manage vector databases such as Pinecone, FAISS, or pgvector.
• Evaluate model performance, reduce hallucinations, and implement monitoring and security.
• Deploy solutions using Docker and cloud platforms.

Required Qualifications

• 7+ years of software engineering experience, including generative AI development.
• Strong Python, SQL, REST API, Git, and testing skills.
• Hands-on experience with LLMs, prompt engineering, RAG, LangChain, or LlamaIndex.

Desired Qualifications

Experience with AWS, Azure, GCP, CI/CD, and PyTorch.

Nice-to-Have

Knowledge of LangGraph, fine-tuning, MLflow, Kubernetes, and LLM evaluation frameworks.