Rathi Anand

About

AI/backend engineer who fine-tuned and deployed a production LLM chatbot using a LangChain + FAISS RAG pipeline, improving latency with PEFT/LoRA and driving strong business impact (40% customer adoption; 92% satisfaction). Also served as technical lead on a data aggregation system for underwriting/quoting, introducing GraphQL for more efficient, maintainable querying and applying CDC to keep cached ranking data fresh at scale.

Key Strengths

• Built and deployed LLM chatbot with RAG (LangChain + FAISS) end-to-end (training + inference)
• Improved LLM production latency by using PEFT/LoRA (training limited weights)
• Drove measurable adoption and satisfaction: 40% of customers shifted to chatbot; 92% satisfaction poll
• Technical lead on data aggregation platform; introduced GraphQL to reduce redundant data and improve maintainability
• Strong quality bar: achieved 100% code coverage before completion
• Scaled backend ranking service by addressing cache misses with CDC-driven cache updates
• Handled reliability incidents using Azure Monitor alerts and Kubernetes graceful shutdown automation
• End-to-end ownership from requirements and architecture through full-stack implementation and production release
• Reusable, templated frontend component system for rapidly building multiple dashboards
• Backend performance optimization using GraphQL to address N+1 query patterns
• Security-focused feature development (authN/authZ, XSS validation, rate limiting, HTTPS, session timeouts)
• Production Python/FastAPI services with API versioning and Pytest-based reliability
• React + TypeScript UI delivery with performance/maintainability patterns (context to avoid prop drilling, useMemo/useCallback)
• PostgreSQL schema design for complex domains and performance tuning (reducing join overhead with temp tables)
• Cloud deployment practices using Docker, caching, horizontal scaling, and resilient retry strategies (exponential backoff with jitter)

Reference Highlights

• Consistently strong product impact
• Reliable delivery of high-visibility work
• On-time delivery with high quality
• Rarely required significant rework after handoff
• Improved user experience and performance
• Excellent communication skills
• Bridges technical and non-technical stakeholders
• Strong end-to-end ownership across stack
• Cohesive full-stack thinking (schema/services/UI aligned)
• Strong database modeling skills
• Performance-aware mindset before shipping to production
• Efficient and proactive in production incident support
• Very good troubleshooter
• Thrives in high-ownership, ambiguous environments
• Turns ambiguous business needs into architecture and shipped product
• Proactively identifies gaps and proposes solutions
• Communicates progress clearly to leadership and earns trust quickly
• Works independently with minimal oversight
• Would work with her again without hesitation
• Consistently delivered production-ready, customer-facing features
• Disciplined approach to engineering
• Well-tested, reliable code
• Improved system errors without user disruptions
• Strong end-to-end full-stack capabilities
• Delivered feature enhancements to 5,000+ users
• Smooth, disruption-free rollouts
• Strong operational reliability and ownership in production
• Quick issue resolution in collaboration with DevOps
• Keeps reliability and user experience in focus
• Performs well in high-ownership and ambiguous environments
• Steps into leadership roles when needed
• Translates business needs into technical solutions
• Drives projects from concept through delivery with minimal oversight
• Coordinates effectively with stakeholders and offshore teams

Experience

Education

Skills

Languages

Publications

2 publications