Description

You will design, deploy, and optimize production-grade AI systems, focusing on LLM pipelines, RAG architectures, and agent-based workflows. You own the reliability, latency, and cost-efficiency of these services.

This role is on-site.

Responsibilities

• Design and develop LLM pipelines, RAG systems, and vector database integrations using Python and FastAPI.
• Optimize system latency and throughput for model calls and retrieval operations to ensure high performance.
• Deploy and scale AI models into production using MLOps frameworks, CI/CD pipelines, and AWS infrastructure.
• Handle incident response for AI systems, resolving slow RAG performance, API rate limits, and unexpected cost spikes.
• Implement observability with OpenTelemetry and collaborate with DevOps teams to maintain system reliability.

Required Skills

• 8+ years of experience in AI/ML model development and production deployment.
• Strong proficiency in Python, FastAPI, and cloud infrastructure (AWS).
• Deep understanding of RAG architecture, LangChain, and Vector Databases.
• Experience with MLOps practices, CI/CD pipelines, and OpenTelemetry.
• Ability to diagnose and resolve performance bottlenecks and cost inefficiencies in AI workloads.

Preferred Skills

• Experience with Gunicorn containerized deployments and LlamaIndex orchestration.
• Familiarity with Pinecone, AWS Knowledgebase, or Chroma vector databases.
• Proven strategies for handling OpenAI outages with fallbacks to smaller models.

Key Skills

Education

Any Graduate