AI Engineer

ClinDCast LLC; Warren Township (NJ); Remote; USD 120,000 - 155,000; Full time

Job summary

ClinDCast LLC is seeking an AI/ML Engineer focused on Generative AI, LLMs and agent-based systems. You will design, develop, and deploy scalable AI solutions in collaboration with cross-functional teams to translate business requirements into reliable AI applications.

You will work with modern frameworks and cloud-based MLOps, build RAG pipelines, implement AI agents, MLOps pipelines, and ensure governance, monitoring, and secure, auditable deployments.

Responsibilities

• Design, fine-tune, and deploy LLM-based solutions for enterprise use cases such as document intelligence, summarization, and conversational AI.
• Build Retrieval-Augmented Generation (RAG) pipelines using vector databases to enhance response accuracy and contextual grounding.
• Develop prompt engineering strategies and evaluation frameworks to ensure output quality, consistency, and safety.
• Integrate LLMs with enterprise systems using frameworks like LangChain, LlamaIndex, or similar tools.
• Evaluate and benchmark different foundation models to select optimal solutions for business needs.
• Architect and implement AI agents capable of multi-step reasoning and task execution.
• Develop agentic workflows using modern design patterns for complex, multi-turn interactions.
• Implement human-in-the-loop mechanisms to ensure compliance, reliability, and risk control.
• Integrate AI agents with APIs, enterprise platforms, and orchestration tools.
• Establish guardrails, monitoring, and audit logging for responsible AI usage.
• Build and maintain end-to-end MLOps pipelines including training, validation, deployment, and monitoring.
• Implement CI/CD pipelines for machine learning models to enable continuous delivery.
• Deploy models as scalable APIs or batch services using cloud-native platforms.
• Monitor model performance for drift, degradation, and anomalies in production.
• Maintain model governance, versioning, and lineage tracking for auditability.
• Collaborate with business stakeholders to translate requirements into AI-driven solutions.
• Participate in Agile/Scrum development processes and contribute to sprint deliverables.
• Create technical documentation including solution designs, APIs, and operational guides.
• Mentor junior team members and contribute to best practices in AI engineering.
• Flexible work from home options available.

Job description

Job Title: AI/ML Engineer – Generative AI & LLM

Job Summary

We are seeking a skilled AI/ML Engineer with expertise in Generative AI, Large Language Models (LLMs), and agent-based systems. The ideal candidate will design, develop, and deploy scalable AI solutions, leveraging modern frameworks and cloud-based MLOps practices to deliver production-grade systems. This role involves close collaboration with cross-functional teams to translate business requirements into intelligent, reliable AI applications.

Key Responsibilities

Generative AI & LLM Development

Design, fine-tune, and deploy LLM-based solutions for enterprise use cases such as document intelligence, summarization, and conversational AI.

Build Retrieval-Augmented Generation (RAG) pipelines using vector databases to enhance response accuracy and contextual grounding.

Develop prompt engineering strategies and evaluation frameworks to ensure output quality, consistency, and safety.

Integrate LLMs with enterprise systems using frameworks like LangChain, LlamaIndex, or similar tools.

Evaluate and benchmark different foundation models to select optimal solutions for business needs.

AI Agents & Intelligent Automation

Architect and implement AI agents capable of multi-step reasoning and task execution.

Develop agentic workflows using modern design patterns for complex, multi-turn interactions.

Implement human-in-the-loop mechanisms to ensure compliance, reliability, and risk control.

Integrate AI agents with APIs, enterprise platforms, and orchestration tools.

Establish guardrails, monitoring, and audit logging for responsible AI usage.

MLOps & Deployment

Build and maintain end-to-end MLOps pipelines including training, validation, deployment, and monitoring.

Implement CI/CD pipelines for machine learning models to enable continuous delivery.

Deploy models as scalable APIs or batch services using cloud-native platforms.

Monitor model performance for drift, degradation, and anomalies in production.

Maintain model governance, versioning, and lineage tracking for auditability.

Collaboration & Delivery

Work with business stakeholders to translate requirements into AI-driven solutions.

Participate in Agile/Scrum development processes and contribute to sprint deliverables.

Create technical documentation including solution designs, APIs, and operational guides.

Mentor junior team members and contribute to best practices in AI engineering.

Flexible work from home options available.