Performance Engineer (AI Platforms & Agents)

🎯 Role Overview

We are seeking highly skilled Performance Engineers with strong expertise in testing AI agents and AI platforms . The ideal candidate will combine deep performance engineering skills with AI awareness , ensuring scalability, reliability, and efficiency of next-generation AI workloads.

🛠️ Key Responsibilities

• Performance Testing of AI agents and platforms, focusing on latency, throughput, and resource utilization.
• Design and execute load and stress tests for AI-driven applications.
• Collaborate with AI developers to identify bottlenecks in model inference and optimize system performance.
• Implement monitoring solutions for AI pipelines , ensuring observability across distributed systems.
• Provide detailed performance reports and recommend optimization strategies .
• Ensure compliance with scalability and reliability standards in cloud AI environments .

📚 Required Skills

• Strong background in performance engineering (load testing, profiling, benchmarking).
• Hands-on experience with tools like JMeter , Locust , or Gatling .
• Familiarity with AI/ML concepts (model training, inference, evaluation metrics).
• Knowledge of GPU/CPU utilization and distributed computing.
• Experience with cloud platforms (Azure AI, AWS Bedrock, Google Vertex AI).
• Strong analytical and problem-solving skills with ability to debug complex performance issues.

✅ Preferred Qualifications

• Exposure to AI observability tools (Prometheus, Grafana, OpenTelemetry).
• Experience with vector databases and caching strategies.
• Prior work on multi-agent systems .
• Understanding of AI evaluation metrics such as accuracy, precision, recall, and hallucination rate.

📍 Location

• Open to candidates in Pune with strong availability.

⏱️ Availability

• Immediate joiners preferred .