Experience

Indian Institute of Technology Delhi · May 2026 to Present

Working on agentic systems for recommendations under Dr. Sandeep Kumar, designing LLM-driven agents that reason over user context and preferences.
Building multi-agent pipelines combining retrieval, planning, and tool use to move beyond static collaborative-filtering baselines.
Developing evaluation methodology for agentic recommenders, including failure-mode characterization and robustness analysis.

Colate · Jul 2025 to Dec 2025

Developed a multi-provider LLM gateway on a shared request/event representation that translates between OpenAI, Anthropic and Gemini formats, covering streaming, tool calls and multimodal inputs.
Implemented prompt caching and token-usage accounting: the internal dashboard reported 6.05B cached input tokens (53% input-token reuse) and 35% lower inference latency from caching and runtime optimizations.
Built multi-agent orchestration for Cana with worker, reviewer and lead roles, dependency-aware delegation, inter-agent messaging and completion handoffs for long-running tasks.
Engineered a vector database and semantic code-search engine, indexing repository-scale corpora for sub-second retrieval.
Shipped persistent AWS/Kubernetes runtimes with session recovery so long-running agent jobs survive restarts without losing context.
Built an evaluation harness across 90+ test prompts to catch robustness regressions before release.

Honors & Awards

IIT Delhi · 2024

Galgotias University · 2024

IIT Delhi (Organized by SIB) · 2023

IIT Bombay · 2023

IILM University · 2023