.png){kind=logo}
Vikram Sandigaru
Mid-level AI Engineer specializing in AI agents, RAG pipelines, and LLM evaluation
Connect with Vikram
Vikram 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 production LLM systems at Founderbay, including a low-latency voice agent and a graph-based multi-agent research assistant. Strong focus on reliability in real workflows—hybrid SERP + full-site scraping RAG, grounding guardrails, validation checkpoints, and transcript-driven evaluation—plus performance tuning with async FastAPI, Redis caching, and containerization. Also partnered with a non-technical ops lead to automate post-call follow-ups via call summarization, field extraction, and tool-triggered actions.
Experience
Education
Key Strengths
- Built and deployed production LLM voice agent with low-latency constraints
- Designed hybrid retrieval (SERP + targeted/full-site scraping) to improve groundedness
- Implemented guardrails and validation steps to reduce hallucinations and prevent guessing on weak context
- Production-oriented evaluation approach using real conversation/edge-case datasets and transcript-based testing
- LangGraph/LangChain orchestration with shared state and router-node tool routing for reliable multi-agent flows
- Performance optimization under load (async FastAPI, Redis caching, containerization)
- Effective collaboration with non-technical stakeholders to translate workflows into LLM tool-calling automation
Discover more candidates like Vikram
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent