.png){kind=logo}
Hanish Kukkala
Mid-level Data Scientist specializing in Generative AI and NLP
Connect with Hanish
Hanish 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
ML/GenAI engineer with recent CVS Health experience building a production RAG system over unstructured financial/research documents using LangChain, FAISS, and Pinecone, plus LoRA/PEFT fine-tuning of GPT/LLaMA for domain-aware summarization. Demonstrates strong applied MLOps and data engineering skills (Airflow/Prefect, Docker/Kubernetes, CI/CD, MLflow) and measurable impact (sub-second retrieval, ~40% better context retrieval, ~25% entity matching improvement).
Experience
Education
Key Strengths
- Built RAG pipeline (LangChain + FAISS + Pinecone) to reduce analyst document review time
- Fine-tuned LLMs (GPT/LLaMA) with LoRA/PEFT in PyTorch for domain-specific summarization
- Improved reliability by mitigating hallucinations via context validation using Sentence-BERT
- Scaled semantic retrieval with FAISS/Pinecone optimization and async retrieval to sub-second latency
- Designed entity resolution pipeline using fuzzy matching + LightGBM; validated with precision/recall/F1
- Improved duplicate matching accuracy by ~25% in multi-system customer/product data
- Improved context retrieval/search relevance by ~40% using embeddings + vector DB + fine-tuning
- Production-grade data workflow practices: orchestration (Airflow/Prefect), containerization (Docker/Kubernetes), CI/CD, testing, MLflow
Discover more candidates like Hanish
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent