INSenior AssociateLLM Observability EngineerApp TechAdvisoryPan India (early joiners)

Job Description & Summary:PwC India is seeking a skilled LLM Observability & Performance Test Engineer tomonitor troubleshoot andoptimizeAI-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 DatadogLangChain orOpenTelemetry.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 monitoringand 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 teamsAutomated Evaluations: Implement automated quality checks and evaluations (e.g. hallucination detection toxicity classifiers relevance scoring) to continuously assess model outputProduction Issues: Utilize tracing and logging data to quickly diagnose the root cause of issues in complex LLM workflows and agenticSecurity and Compliance: Monitor model behavior for potential security risks such as prompt injections or sensitive data leaks and ensure compliance with data protectionCosts: Track and manage token usage and computational resource consumption to ensure cost-effectiveness and alert teams to potential budgetand 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 tomonitor troubleshoot andoptimizeAI-powered applications. This role is crucial for ensuring our large language model systems are performant reliable andcost-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 orwith the unique challenges of LLMs including non-determinism hallucinations and promptwith LLM observability platforms and tools (e.g. Datadog LLM ObservabilityArizeAILangfuse) is highlyin programming/scripting languages (e.g. Python Java).Excellent analytical problem-solving and communication skills.

Preferred skill sets:

Relevant certifications inLLM Observability & Performance Test Engineerare a plus

AppDynamicsDataDogis an added advantage

Years of experience:

3 to 7 years

Education qualification:

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