Senior LLM Observability and Performance Test Engineer

Job Description & Summary: PwC India is seeking a skilled LLM Observability & Performance Test Engineer to monitor, troubleshoot, and optimize AI-powered applications. This role is crucial for ensuring our large language model systems are performant, reliable, and 
cost-effective in real-world scenarios by combining robust performance engineering practices with specialized LLM observability techniques. 

Responsibilities: 

Design and Execute Performance Tests: Develop and implement comprehensive test plans and scripts to evaluate the performance, scalability, and stability of LLM applications under various loads. Implement LLM Observability: Instrument LLM applications to capture rich telemetry data, including prompts, responses, token usage, latency, and error information, using specialized tools and frameworks like Datadog, LangChain, or OpenTelemetry. Monitor and Analyze Metrics: Track key performance indicators (KPIs) such as response time, throughput, cost per query, accuracy, and resource utilization using real-time dashboards and monitoring systems.Identify and Mitigate Bottlenecks: Analyze performance test results and production data to pinpoint performance bottlenecks, errors, and potential issues (e.g., high latency in RAG pipelines) and collaborate with development teams onoptimization.Conduct Automated Evaluations: Implement automated quality checks and evaluations (e.g., hallucination detection, toxicity classifiers, relevance scoring) to continuously assess model output quality.Troubleshoot Production Issues: Utilize tracing and logging data to quickly diagnose the root cause of issues in complex LLM workflows and agentic applications.Ensure Security and Compliance: Monitor model behavior for potential security risks, such as prompt injections or sensitive data leaks, and ensure compliance with data protection regulations.Optimize Costs: Track and manage token usage and computational resource consumption to ensure cost-effectiveness and alert teams to potential budget overruns.Collaborate and Report: Work closely with data scientists, ML engineers, and QA teams to provide actionable insights and recommendations for model fine-tuning and system architecture improvements. 

Mandatory skill sets: 

Seeking a skilled LLM Observability & Performance Test Engineer to monitor, troubleshoot, and optimize AI-powered applications. This role is crucial for ensuring our large language model systems are performant, reliable, and cost-effective in real-world scenarios by combining robust performance engineering practices with specialized LLM observability techniques. 

Strong knowledge of performance testing methodologies and load testing tools such as JMeter, LoadRunner, or Gatling.Familiarity with the unique challenges of LLMs, including non-determinism, hallucinations, and prompt sensitivity.Experience with LLM observability platforms and tools (e.g., Datadog LLM Observability, Arize AI, Langfuse) is highly desirable.Proficiency in programming/scripting languages (e.g., Python, Java).Excellent analytical problem-solving, and communication skills. 

Preferred skill sets: 

• Relevant certifications in LLM Observability & Performance Test Engineer are a plus 

• AppDynamics, DataDog is an added advantage 

Years of experience required: 

3+ to 7 years 

Education qualification: 

B.E. / B.Tech / MCA/ M.E/ M.TECH/ MBA/ PGDM. All qualifications should be in regular full-time mode with no extension of course duration due to backlogs