.png){kind=logo}
Arunim Samudra
Mid-Level Software Engineer specializing in LLM applications, RAG, and OCR automation
Connect with Arunim
Arunim 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
At Trellis, built and shipped a production multi-agent, authenticated GenAI chatbot for sensitive financial account inquiries (loan/payment lookups), using dynamic model routing to control latency and cost while improving accuracy. Implemented prompt-injection defenses (Meta Prompt Guard), RAG with LangChain, and LLM-as-a-judge evaluation; the system cut manual support call volume by 40%+ and was refined through close collaboration with QA-driven user testing.
Experience
Education
Key Strengths
- Built and deployed a secure multi-agent financial support chatbot to production
- Reduced manual support calls by 40%+ through automation
- Designed dynamic query-to-model routing using intent classification and confidence thresholds to balance cost/latency vs accuracy
- Security-first LLM deployment handling sensitive account data (prompt injection filtering with Meta Prompt Guard)
- Strong evaluation discipline using LLM-as-a-judge with rubric scoring for agent/workflow reliability
- Practical RAG implementation with LangChain (vector stores, document pipelines, conversation memory)
- Effective collaboration with non-technical QA stakeholders to improve tone/helpfulness and retrieval robustness via user-centric testing
Discover more candidates like Arunim
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent