.png){kind=logo}
Ashwini Ramesh Kumar
Junior AI Software Engineer specializing in LLMs, RAG, and agent workflows
Connect with Ashwini
Ashwini 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/ML-leaning engineer who built a content-based event recommender for FlowMingle using embeddings + HNSW vector search on Google Cloud, with Firebase as the backend and a managed recommendation lifecycle (15 recs/user, daily async generation, weekly deletion) now serving 1500+ users. Also led a cost-driven migration of ConvAI services to Azure AI using parallel request testing from a Unity client, with post-migration monitoring via logs and model evals; contributed to a Massachusetts law-enforcement conversation analysis system by expanding ingestion to PDF/TXT/Excel and multi-file inputs.
Experience
Education
Key Strengths
- Designed and shipped vector-search recommender (HNSW/ANN) used by 1500+ users
- Strong architectural tradeoff analysis (transformer vs vector search; cold-start, cost, inference/retraining)
- Cost/performance optimization in NoSQL/Firebase via tuning k, soft deletion, and recommendation lifecycle management
- Incremental migration strategy with parallel testing and cutover (ConvAI to Azure AI) to reduce scaling costs
- Production monitoring mindset (logs + periodic evals/analytics for model correctness and quality)
- Proactively identified real-world edge cases (multi-format, multi-file inputs) for law-enforcement conversation analysis tooling
Discover more candidates like Ashwini
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent