.png){kind=logo}
Kumar Manik
Intern AI Engineer specializing in LLMs, MLOps, and RAG systems
Connect with Kumar
Kumar 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 shipped a production-grade RAG-powered news summarization and Q&A product, tackling real-world issues like retrieval drift, hallucinations, latency, and autoscaling deployment (Docker + FastAPI + Streamlit Cloud). Experienced in end-to-end ML/LLM workflow automation using Airflow, Kubeflow Pipelines, and MLflow, and has demonstrated business impact (40% inference precision improvement) through close collaboration with non-technical stakeholders at Evoastra Ventures.
Experience
Education
Key Strengths
- Built and deployed production RAG news summarization + Q&A system
- Mitigated retrieval drift with time-decay scoring and TTL-based vector index pruning
- Reduced hallucinations via strict source-grounded prompting and answer verification checks
- Improved real-time latency using lightweight embeddings, batched API calls, and caching
- Scaled deployment with Docker containerization and autoscaling (Streamlit Cloud + FastAPI)
- Established feedback loops: monitoring real queries/failures, confidence scoring, and user testing
- Designed reproducible end-to-end ML workflows integrating Airflow, Kubeflow Pipelines, and MLflow
- Bridged technical/non-technical gap; delivered solution improving inference precision by 40% (internship project)
Discover more candidates like Kumar
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent