remoteonsite
AI/ML Engineer - TechLatern Solutions
ML Engineer
AI/ML Engineer focused on building and deploying LLM-powered applications and AI agents using OpenAI, Anthropic Claude, Gemini, Hugging Face, LangGraph, CrewAI, and RAG pipelines.
About the role
Key Responsibilities
- Design, prototype, and deploy LLM-based applications leveraging OpenAI, Anthropic Claude, Gemini, and Hugging Face models.
- Build and orchestrate AI agents and multi‑agent systems with LangGraph, CrewAI, AutoGen, and MCP (Model Context Protocol).
- Implement Retrieval‑Augmented Generation (RAG) pipelines to enhance model accuracy and relevance.
- Collaborate with data, product, and DevOps teams to integrate AI solutions into production environments.
- Monitor, evaluate, and iterate on model performance, ensuring scalability and reliability.
Requirements
- 2–8 years of experience in AI/ML engineering with a strong focus on LLMs and generative models.
Skills
pythonraggenerative ai