.png){kind=logo}
Pravalika Kuppireddy
Mid-level AI/ML Engineer specializing in Generative AI and intelligent automation
Connect with Pravalika
Pravalika already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Recommended
Already have an account?
About
LLM engineer who built and productionized a system to classify GitHub commits (performance vs non-performance) using zero-/few-shot approaches over commit messages and diffs, working at ~5M-record scale on multi-node NVIDIA GPUs. Experienced orchestrating end-to-end LLM pipelines with Airflow and GitHub Actions, and emphasizes reliability via testing, guardrails, and observability while collaborating closely with non-technical product stakeholders.
Experience
Education
Key Strengths
- Built and deployed an LLM-based GitHub commit classifier (performance vs non-performance) to production
- Scaled LLM experimentation on very large datasets (~5M records) using multi-node NVIDIA GPUs
- Pragmatic tradeoff analysis between latency and classification quality (commit message-only vs message+diff tokens)
- Designed end-to-end LLM fine-tuning and evaluation pipelines with Airflow DAGs (including metadata passing via XComs)
- Reliability-focused agent/workflow evaluation using unit tests, synthetic edge cases, end-to-end validation, and production guardrails
- Strong cross-functional communication: translated LLM/embedding concepts for a non-technical PM and used a demo dashboard to drive feedback
Discover more candidates like Pravalika
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent