AI ML Engineer

Job Title: AI/ML Engineer – LLM Platform & Model Management (AWS/GCP)

Experience: 5+ Years

Location: Remote (Aligned with U.S. Working Hours)

Job Summary

We are seeking a highly skilled AI/ML Engineer with strong expertise in LLM platforms, MLOps, and cloud-based model management. The ideal candidate will have hands-on experience in deploying, scaling, and optimizing machine learning models across AWS and GCP environments, with a key focus on migrating workloads from Google Vertex AI to Amazon SageMaker.

You will play a critical role in building scalable LLM-driven systems, implementing multi-model orchestration, and designing AI-powered document processing

pipelines.

Key Responsibilities

Model Management & Deployment

• Design, deploy, and manage ML models using Amazon SageMaker

• Lead migration of ML workloads from Google Vertex AI to AWS

• Implement model versioning, monitoring, and lifecycle management

• Build scalable real-time and batch inference pipelines

• Optimize model performance, latency, and cost

LLM Integration & Optimization

• Integrate and manage LLM APIs (e.g., Gemini, Claude, Llama, Titan)

• Develop multi-model routing strategies and fallback mechanisms

• Benchmark models based on accuracy, latency, and cost efficiency

• Optimize prompt engineering and inference workflows

API Gateway & LLM Orchestration

• Deploy and configure LiteLLM as a unified LLM gateway

• Enable seamless switching across multiple LLM providers

• Design and expose scalable AI APIs for enterprise applications

Cloud Infrastructure & Security

• Build and deploy containerized applications using:

o Amazon ECS Fargate o Kubernetes (EKS preferred)

• Manage secure access using AWS IAM roles and policies

• Ensure high availability, scalability, and security compliance

Document Processing & AI Workflows

• Build pipelines for:

o Document extraction o Summarization o Classification

• Design and implement RAG-based architectures and semantic search systems

• Optimize performance for large-scale document processing workloads

Required Qualifications

• Bachelor's or Master's degree in Computer Science, Data Science, or related field • 5+ years of experience in AI/ML and MLOps • Strong hands-on experience with:

o AWS SageMaker o Google Vertex AI

• Proven experience with LLMs and Generative AI platforms

• Proficiency in containerization and distributed systems

Core Skills

• MLOps & LLMOps

• Model Deployment, Monitoring & Versioning

• API Integration & Gateway Design

• Cloud Platforms: AWS & GCP

• Microservices & Scalable Architecture

Intrested Candidates Send your Updated Resume to [Confidential Information]/[HIDDEN TEXT]