Work Experience

My work experiences across different companies and roles.

All Experiences(5 experiences)

Lenskart

Lenskart

Working

AI Engineer

July 2026 - Present

Aerocity, New Delhi, India (On-site)

What I've done

  • Building three internal AI systems on Lenskart's AI Engineering team: a hiring intelligence platform, a CEO intelligence brief, and a competitor creative-intelligence platform.
  • Made candidate searches survive crashed workers and provider outages. A lease-and-heartbeat state machine over Postgres reclaims a dead worker's in-flight work, and per-provider failure classification falls back across 4 LLM providers mid-search.
  • Made candidate ranking explainable and repeatable. A deterministic 4-key comparator (score, evidence coverage, confidence tier, name) replaced one opaque LLM score, and identity dedup sends ambiguous matches to human review instead of auto-merging them.
  • Made sure no claim reaches the CEO brief on one weak source. An evidence layer admits a claim only on 1 primary or 3+ independent origins above 0.75 match confidence. Built end to end: 40 source connectors, a 9-tool MCP server backing 18 curation skills, and a measured cost of $1.09 per curation session.
  • Replaced a creative-analysis pipeline that fabricated 27% of its rows (78 of 287). In the new 7-layer FastAPI and Next.js platform, a deterministic guardrail checks every generated figure against tool evidence instead of trusting an LLM judge.
  • Raised LLM-judge agreement with human labels from 54% to 89% (27 held-out labels in the latest batch) with a tiered judge (deterministic checks, then a classifier, then LLM review), planted-error tests, an overfit audit and a regression gate.
C3alabs

C3alabs

Software Engineer (Part-time)

October 2025 - October 2026

New Jersey, United States (Remote)

What I've done

  • Built and shipped production AI agent systems on a multi-tenant agent platform: a FastAPI agent engine, a Django API layer, and a Next.js workflow editor.
  • Cut cost and latency in the multi-agent orchestrator: rewrote the classifier and planner prompts (19.1K to 5.4K and 22.8K to 9.5K characters, roughly 3,300 tokens saved per request each), fixed a prompt-cache invalidation bug by moving query-dependent context below the cache boundary (23.6K tokens cached per request, a 35 to 42% cost saving), and parallelized context assembly that had been running as sequential awaits. Verified by 125 passing tests.
  • Audited and fixed the agentic workflow engine across 3 repositories: 21 defects including roughly 50 code paths returning success on 4xx and 5xx errors, collapsed 3 tool-router handshakes to 1 on linear runs by detecting linear-versus-DAG topology, removed a hard tool allowlist that had caused a 15-turn failure loop, and moved a 900-second blocking test-run call to a background thread with WebSocket delivery.
  • Built a bot-free meeting-ingestion path that polls the Google Meet API on a schedule instead of running a paid recording bot, plus a vector re-key migration that re-scopes orphaned embeddings to their meeting without re-embedding, covered by 10 tests.
  • Migrated the production memory layer across a breaking Mem0 v1 to v2 upgrade, fixing silently broken call sites where the API had changed sync behavior, prompt contracts, filter requirements, and method signatures.
  • Ran code-grounded reliability and token-efficiency audits of the agent backend, surfacing a permissive CORS configuration on production hosts, 17 fire-and-forget async tasks with no error handling, a cross-user memory leak between agents, and verbatim tool output re-sent every turn as the largest remaining cost lever.
ArmorIQ

ArmorIQ

Full Stack Developer Intern (Part-time)

June 2026 - October 2026

Remote

What I've done

  • Built across the ArmorIQ platform as a part-time 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.
RAAPID INC

RAAPID INC

ML Researcher

April 2025 - July 2026

Louisville, US (Remote)

Technologies & Tools

What I've done

  • Co-authored a research paper on parameter-efficient LLM fine-tuning - arXiv:2601.00231
  • Co-developed GRIT, a curvature-aware LoRA method (K-FAC preconditioning, Fisher-guided reprojection, dynamic rank) that trains about 46% fewer parameters than LoRA on average (25 to 80% by task) while matching or surpassing LoRA and QLoRA.
  • Results on Llama-3.2 3B and Llama-3.1 8B across 5 benchmarks: on Alpaca, within 1% of the best ROUGE and BERTScore with 8.45M trained parameters on 3B (65.3% fewer than LoRA) and 19.27M on 8B (77.0% fewer); top ROUGE-1/2/L and BLEU on Dolly-15k 3B with 30.0% fewer; the best GSM8K accuracy on 8B (0.6619) with 27.8% fewer.
  • Ran benchmark evaluations and ablations (no K-FAC, no reprojection, fixed vs dynamic rank, reprojection frequency) against IA3, DoRA, Orthogonal-LoRA and Shampoo baselines.
Kartavya Technology

Kartavya Technology

AI Agent Developer Intern

June 2025 - August 2025

Bengaluru, India (Remote)

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.

“A man who is master of patience is master of everything else.”

~ George Savile

© 2026 Mohit Goyal