Senior MLOps Engineer

Senior MLOps Engineer (LLM / Agentic Systems)

We are seeking a Senior MLOps Engineer to build and scale intelligent, data-driven platforms for next-generation AI systems. This role focuses on developing LLM-powered applications, agentic workflows, and robust evaluation systems that enable faster insights, improved diagnostics, and reliable large-scale AI deployments.

Key Responsibilities:

• Build and deploy LLM-powered applications and agentic workflows in production
• Design automated evaluation frameworks for measuring LLM performance and detecting regressions
• Integrate AI/ML models into scalable backend systems and pipelines
• Run ML experiments and apply statistical analysis to validate improvements
• Develop and maintain distributed systems for large-scale inference
• Optimize systems for latency, cost, and reliability (caching, batching, prompt tuning)
• Implement guardrails, fallbacks, and monitoring for AI systems
• Work with streaming pipelines and async orchestration for real-time processing

Required Qualifications:

• 3+ years of experience in backend or distributed systems engineering
• Strong programming skills in Python
• Working knowledge of Go, TypeScript, or Rust
• Experience shipping production AI/LLM systems at scale
• Hands-on experience building agentic systems (agents, tools, or workflows)

Strong understanding of:

• Token limits and cost optimization
• Prompt design and structured outputs
• API rate limits and failure handling
• Experience with LLM evaluation methods and challenges (non-determinism, quality measurement)
• Strong knowledge of AWS, GCP, or Azure
• Hands-on experience with Docker and Kubernetes

Preferred Qualifications:

• Experience with agent orchestration frameworks (Lang Graph, Crew AI, etc.)