Description

You will design, build, and operate Large Language Model and Small Language Model capabilities for the enterprise Agent Factory, transforming foundation models into secure, reusable AI services.

This role is remote.

Responsibilities

• Build production-grade LLM, GenAI, and agentic AI solutions using RAG, prompt engineering, and APIs.
• Implement reusable prompt and context engineering frameworks alongside enterprise RAG patterns and retrieval services.
• Deploy and host models (cloud, hybrid, on-prem) with secure inference APIs for internal agents.
• Develop model evaluation pipelines, benchmarking, and AI quality dashboards for accuracy and latency.
• Integrate MCP, tool registries, and agent runtimes into enterprise workflows and developer platforms.

Required Skills

• 7+ years of software, AI, or platform engineering experience.
• 2+ years hands-on experience building LLM, GenAI, or agentic AI solutions.
• Deep expertise in LLM application development, RAG, and prompt/context engineering.
• Experience with model evaluation, prompt testing, and AI quality measurement.
• Proficiency in integrating AI capabilities into enterprise applications and workflows.
• Knowledge of model serving, hosting, and optimization in cloud or on-prem environments.
• Experience with MCP, tool registries, or agent runtimes.

Preferred Skills

• Experience deploying open-source models (Llama, Mistral, etc.) on GPU infrastructure (NVIDIA/AMD).
• Background in regulated industries (healthcare, financial services) with Responsible AI and governance practices.

Key Skills

Education

Any Graduate