.png){kind=logo}
Siddhardha Kanamatha
Mid-level AI/ML Engineer specializing in LLMs, RAG, and MLOps
Connect with Siddhardha
Siddhardha 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
ServiceNow engineer who built and launched a production LLM-powered ticket resolution/knowledge assistant using RAG (LangChain + Hugging Face embeddings + vector search) integrated into internal support dashboards via REST APIs. Optimized the system from ~6–8s to ~2–3s latency while improving usability with concise, cited answers and guardrails (grounding + similarity thresholds), delivering ~30–35% reduction in manual ticket investigation effort.
Experience
Education
Key Strengths
- Owned and shipped production LLM/RAG support-ticket assistant end-to-end (ingestion → embeddings/vector search → LangChain RAG → REST API integration)
- Drove measurable impact: reduced manual ticket investigation effort ~30–35% and improved support response times
- Balanced latency vs quality via retrieval-depth tuning (10–12 docs down to 3–5), chunking/index optimizations, and model routing (mid-size default, larger model for complex queries)
- Implemented practical LLM guardrails (retrieval grounding, similarity-score thresholds, fallback to articles/search) to reduce hallucinations
- Built evaluation loop combining curated test set, automated retrieval/generation metrics, and human engineer review; iterated prompts to improve actionability
Discover more candidates like Siddhardha
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent