.png){kind=logo}
Nishitha Thummala
Mid-level AI/ML Engineer specializing in LLMs, RAG, and scalable inference
Connect with Nishitha
Nishitha 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
Backend/retrieval-focused engineer with production experience at Perplexity building a large-scale real-time Q&A system using retrieval-augmented generation, emphasizing low-latency, high-quality answers through ranking, context optimization, and caching. Also has orchestration experience from both product-facing LLM pipelines and large-scale infrastructure workflows at Meta, and has partnered with non-technical stakeholders to align AI trade-offs with business goals.
Experience
Education
Key Strengths
- Built and optimized production RAG pipeline for real-time Q&A at scale
- Strong trade-off management between accuracy, latency, and cost in LLM systems
- Improved retrieval quality via ranking and query-document matching to reduce hallucinations
- Reliability engineering for multi-step AI workflows (retries, fallbacks, timeouts)
- Pragmatic evaluation approach using component tests plus end-to-end tests with production query replays
- Effective cross-functional communication translating business goals into technical changes
Discover more candidates like Nishitha
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent