.png){kind=logo}
Sri Harsha patallapalli
Mid-level Machine Learning & Data Infrastructure Engineer specializing in MLOps on AWS
Connect with Sri
Sri 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
Built and deployed a fine-tuned Qwen 2.5 14B model into production at Dextr.ai as the backbone for hotel-operations agentic workflows, running on AWS EKS with Triton and TensorRT-LLM. Demonstrates strong cost-aware LLM engineering (QLoRA, FP8/BF16 on H100) plus rigorous benchmarking/observability (Prometheus, LangSmith) with reported sub-30ms TTNT. Previously handled long-running ETL orchestration with Airflow at GE Healthcare and Lowe's.
Experience
Education
Key Strengths
- Production deployment of fine-tuned LLM to AWS EKS using Triton + TensorRT-LLM
- Cost/performance optimization under tight budget using QLoRA and mixed precision (FP8/BF16) on H100
- Performance benchmarking and observability with Prometheus; achieved sub-30ms TTNT
- Model quality evaluation using BLEU and perplexity
- Orchestrated long-running ETL pipelines with Airflow; improved reliability and parallelization
- Agent workflow tracing and bottleneck analysis with LangSmith (CoT traces, token consumption, latency)
- Cross-functional collaboration with non-technical cofounder via daily huddles and iterative course-correction
Discover more candidates like Sri
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent