Machine Learning Engineer

ClifyX; Town of Florida (NY); On-site; USD 120,000 - 190,000; Full time

Job summary

ClifyX is seeking a Machine Learning Engineer to design, build, and deploy Generative AI solutions powered by Large Language Models. You will work on end-to-end GenAI use cases, from model selection to production-ready systems, integrating open-source and closed-source LLMs.

The role involves developing production-grade GenAI applications, designing agentic workflows with LangChain and LangGraph, and collaborating with product and platform teams to deliver scalable AI solutions.

Qualifications

• Experience with LLMs (OpenAI, Anthropic, Llama, Mistral).
• Hands-on experience with LangChain and LangGraph.
• Solid understanding of LLM memory architecture and state management.
• Proficiency in Python and ML engineering best practices.

Responsibilities

• Design, build, and deploy GenAI applications using LLMs (open-source and closed-source).
• Develop production-ready GenAI workflows and systems.
• Create agentic workflows using LangChain and LangGraph.
• Collaborate with product and platform teams to deliver scalable AI solutions.

Skills

LLMs experience

LangChain/LangGraph

Python

Memory architecture & state management

Tools

LangChain

LangGraph

Python development tooling

Job description

We are seeking a Machine Learning Engineer to design, build, and deploy Generative AI solutions powered by Large Language Models (LLMs). In this role, you will work on end-to-end GenAI use cases, from model selection to production-ready systems. Key Responsibilities Develop and productionize GenAI applications using LLMs (open-source and closed-source). Design agentic workflows using LangChain and LangGraph.

Must Have Technical/Functional Skills:

Must Have Technical/Functional Skills:

• Implement short-term and long-term memory strategies for LLM-based systems.
• Optimize prompts, retrieval pipelines, and orchestration logic.
• Collaborate with product and platform teams to deliver scalable AI solutions.

We are seeking a Machine Learning Engineer to design, build, and deploy Generative AI solutions powered by Large Language Models (LLMs). In this role, you will work on end-to-end GenAI use cases, from model selection to production-ready systems. Key Responsibilities Develop and productionize GenAI applications using LLMs (open-source and closed-source). Design agentic workflows using LangChain and LangGraph.

Required Qualifications

• Strong experience with LLMs (e.g., OpenAI, Anthropic, Llama, Mistral)
• Hands-on experience with LangChain and/or LangGraph.
• Solid understanding of LLM memory architecture and state management.
• Proficiency in Python and ML engineering best practices.

Nice to Have

• Experience with GCP services (e.g., Vertex AI, BigQuery, GCS).
• Experience deploying ML/GenAI systems in production environments.
• data scientist
• Design, develop, and deploy GenAI applications using LLMs.
• Build and implement agentic workflows using LangChain/LangGraph.
• Develop ML models and production-ready AI solutions.
• Implement and manage LLM memory and state management strategies.
• Optimize prompts, retrieval pipelines, and orchestration workflows.
• Collaborate with product and platform teams to deliver scalable AI solutions.
• Deploy, monitor, and maintain AI/ML systems in production environments.
• Evaluate and integrate open-source and proprietary LLMs.