Gen AI Engineer

We are looking for a highly skilled AI Engineer with 4+ years to join our team and lead the development and deployment of advanced AI systems. You will work with large language models (LLMs), build RAG and agentic workflows, evaluate custom models, and integrate cloud-based AI services. This role offers the opportunity to contribute to cutting-edge conversational AI applications and autonomous agents.

Key Responsibilities

Develop and fine-tune applications using LLMs (e.g., OpenAI, Claude, Gemini).

Deploy and manage custom open-source models (e.g., LLaMA, DeepSeek).

Design and implement Retrieval-Augmented Generation (RAG) workflows.

Build and maintain AI agentic workflows for autonomous task execution.

Conduct model evaluation and performance benchmarking.

Leverage cloud AI services (AWS, GCP, or Azure) for scalable deployment.

[Optional] Integrate with the MCP server for interactive applications.

[Optional] Work with conversational AI characters (e.g., Convai).

Required Qualifications

Proven experience working with foundation models and LLM APIs.

Hands-on experience in deploying open-source models in production.

Solid understanding of vector stores and RAG architectures.

Experience with multi-step AI agent frameworks or toolchains (LangChain, AutoGen, etc).

Strong knowledge of cloud services for AI workloads.

Familiarity with prompt engineering, model evaluation techniques, and observability.