Work Experience

Technologies & Tools

What I've done

• Building the candidate-discovery layer of Lenskart's internal AI recruiting platform on the AI Engineering team (Gurugram HQ, on-site).
• Built a multi-provider LLM sourcing pipeline that grounds every candidate result in live web search and falls back across providers for reliability.
• Designed a resumable, Postgres-backed search pipeline that merges candidates from multiple sources, deduplicates them by identity, and ranks them with a deterministic, explainable comparator rather than one opaque LLM score.
• Built a per-job LLM cost ledger that prices token usage per provider and model and enforces spend caps across the pipeline.

Technologies & Tools

What I've done

• Built and deployed production-grade AI systems at C3ALabs, focusing on reliability, latency, and real-user usage not demos.
• Developed agentic AI features (artifacts, agent skills, multi-agent orchestration) and shipped them to production, ensuring performance under real-world constraints.
• Designed and productionized advanced RAG pipelines using Google File Search APIs, handling document chunking, retrieval quality, and response grounding in production environments.
• Core contributor to applied AI R&D experimented with Claude skills, MCP-based tool routing (Composio), and multi-agent coordination patterns, turning research ideas into deployable systems.

Technologies & Tools

What I've done

• Building across the ArmorIQ platform as a full-stack engineer, spanning backend APIs, the React console, AI-agent features, performance, and security.
• Built the observability system end to end: instrumented the SDK's core operations as nested trace spans, then built the ingest API, Postgres store, and query endpoints that persist and serve those traces.
• Hardened an LLM-powered policy-authoring feature with guardrails that reject fabricated tool references and sanitize untrusted input before it reaches the model.
• Shipped security and performance work on the backend, including tenant-isolation fixes on the policy engine and a redesign of API rate limiting into isolated per-route buckets.
• Built a documentation MCP server from scratch in Python (FastMCP) with API-key auth, per-IP rate limiting, and a CI-gated search-quality eval, deployed on Google Cloud Run.

Technologies & Tools

What I've done

• Co-authored a research paper on parameter-efficient LLM fine-tuning - arXiv:2601.00231
• Co-developed GRIT, a geometry-aware PEFT method using K-FAC preconditioning, Fisher-guided reprojection, and dynamic rank adaptation, that fine-tunes under 1% of a model's parameters while outperforming full fine-tuning and LoRA on standard benchmarks.
• Ran ablation studies comparing GRIT against LoRA, QLoRA, and AdaLoRA across multiple LLMs and standard NLP benchmarks.

Technologies & Tools

What I've done

• Autonomous Market Research Agent: Developed an agent that automates market and competitor research using real-time data collection, web search, and report generation for business insights.
• AI Voice Interviewer: Built and deployed a voice-based AI interviewer to conduct inbound calls, capture candidate responses, and generate structured interview summaries.
• Personalized Front Desk Agent: Created a multimodal front desk AI agent capable of handling text, voice, and video inquiries for customer support and client onboarding processes.
• Whatsapp and Social Media Automation Agent: Engineered agents that automate group administration, content posting, and engagement analysis on WhatsApp and other social platforms.
• Credit Risk Analysis Agent: Designed a credit risk agent using custom ML models to evaluate applicant default risk and streamline lending decisions with automated scoring and documentation.
• Outbound Calling Platform Agent: Deployed outbound calling agents capable of scheduling, executing, and logging calls for lead generation and customer feedback with seamless voice pipeline integration.