.png){kind=logo}
Krishna K
Junior Machine Learning Engineer specializing in multimodal systems and LLMs
Connect with Krishna
Krishna 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 productionized a domain-specific LLM-powered RAG knowledge assistant at JerseyStem for answering questions over large internal document corpora, owning the full stack from FAISS retrieval and LoRA/QLoRA fine-tuning to AWS autoscaling GPU deployment. Drove measurable gains (28% accuracy lift, 25% latency reduction) and improved reliability through hybrid retrieval, grounded decoding, preference-model reranking, and Airflow-orchestrated pipelines (35% faster runtime), while partnering closely with non-technical stakeholders to define success metrics and ensure adoption.
Experience
Education
Key Strengths
- Built and deployed production domain-specific LLM RAG system for enterprise document QA
- End-to-end ownership (ingestion, retrieval, fine-tuning, reranking, AWS GPU autoscaling deployment)
- Reduced hallucinations via hybrid retrieval, strict document versioning, and grounded decoding with preference-model reranking
- Improved contextual accuracy by 28% and reduced inference latency by 25%
- Automated RAG data curation/evaluation with Airflow DAGs, cutting pipeline runtime by 35% and preventing stale embeddings
- Strong reliability engineering for AI workflows (modular design, layered testing, SLAs, drift/regression monitoring, canary/A-B releases)
- Effective collaboration with non-technical stakeholders to define metrics, prioritize features, and drive adoption
Discover more candidates like Krishna
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent