.png){kind=logo}
Harsh Chaudhari
Intern Software Engineer specializing in ML/NLP and LLM applications
Connect with Harsh
Harsh 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
Full-stack AI/LLM engineer who has deployed a production LLM backend (Mistral 14B) on GKE to auto-transform datasets and generate runnable ML training pipelines, addressing hallucinations, schema mismatch, latency, and burst scaling with caching/prompt compression and HPA. Also has internship experience (Splunk, BlackOffer) delivering data automation and 10+ Power BI dashboards for non-technical stakeholders with measurable efficiency gains.
Experience
Education
Key Strengths
- Built and deployed an LLM-powered dataset transformation + ML pipeline/code generation system to production on GKE
- Improved LLM reliability via schema validation/guards to reduce hallucinations and schema mismatch
- Performance optimization under load: caching + prompt compression to reduce latency
- Production scaling experience: implemented Kubernetes horizontal pod autoscaling to handle traffic bursts
- Structured AI agent/workflow evaluation using KPIs (accuracy, latency, cost, success rate) and modular pipeline design
- Testing rigor: unit tests plus A/B comparisons across model versions using real-world datasets
- Cross-functional delivery: built Python automation pipelines and 10+ Power BI dashboards for business stakeholders
- Quantified business impact: reduced data preparation time by 25% and improved reporting speed by 20%
Discover more candidates like Harsh
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent