Sanyam Lakhanpal

AI Researcher

San Francisco, California, United States4 yrs 8 mos experience

AI EnabledAI ML Practitioner

Key Highlights

Expert in architecting production-scale LLM systems.
Proven track record in developing autonomous AI agent systems.
Strong background in multimodal AI and optimization techniques.

Stackforce AI infers this person is a Machine Learning Engineer specializing in AI systems and infrastructure for enterprise solutions.

Contact

Skills

Core Skills

Large Language Model Operations (llmops)Multi-agent SystemsRetrieval-augmented Generation (rag)Large Language Models (llm)Bayesian OptimizationData Science

Other Skills

FastAPILangChainRedisDistributed SystemsDockerKubernetesAgent-based ModelingAmazon Web Services (AWS)PyTorchC++Distributed TrainingCommunicationMathematicsPython (Programming Language)Java

About

Senior Machine Learning Engineer with 4+ years of industry experience specializing in production-scale LLM systems, agentic AI, and high-performance ML infrastructure. Built autonomous AI agent systems with advanced RAG architectures, multi-agent orchestration, and dual-layer memory systems. Architected production pipelines and engineered self-reflective agent frameworks. Core Expertise Agentic AI & RAG Systems, LLM Optimization and SFT, Voice Agent Systems, Multimodal AI: Vision-language models, Customised MMOE arch. Research Background Graduate researcher under Prof. Kookjin Lee at Arizona State University, advancing vision-language integration, cross-modality retrieval, and transformer optimization Previously: Senior Software Engineer at C3.ai | ML Engineer at Zoho | Software Engineering Intern at Amazon

Experience

4 yrs 8 mos

Total Experience

1 yr 5 mos

Average Tenure

5 mos

Current Experience

Regulis ai

Member of Technical Staff

Dec 2025 – Present · 5 mos · San Francisco Bay Area · On-site

Cayu technologies

Member of Technical Staff

Jul 2025 – Nov 2025 · 4 mos · San Francisco Bay Area · On-site

Architecting scalable voice agent platforms with automated evaluation pipelines and AI-driven quality insights that accelerate decision-making workflows. Building intelligent multi-channel orchestration systems that seamlessly integrate voice and messaging services with adaptive context awareness.

FastAPILangChainLarge Language Model Operations (LLMOps)Multi-agent SystemsRedisDistributed Systems+2

C3 ai

Senior Software Generative AI Engineer

Jul 2024 – Jun 2025 · 11 mos · Redwood City, California, United States

Architected production-scale agentic AI systems with advanced RAG pipelines with increased accuracy improvements over legacy OCR. Engineered multi-agent orchestration frameworks with reflection loops and dual-layer memory systems, increasing long-horizon task success rates.

Retrieval-Augmented Generation (RAG)Agent-based ModelingAmazon Web Services (AWS)Large Language Models (LLM)

Ira a. fulton schools of engineering at arizona state university

Graduate Student Assistant

May 2022 – Jul 2022 · 2 mos · Tempe, Arizona, United States

Worked with Prof. Kookjin Lee on optimizing Multimodal Variational auto-encoders and experimenting with products of expert models for Fake News and Meme detection.
Authored the work on the paper "A multi-ethnic approach to identifying anti-Asian racism in social media" by fine tunning the ensembled LLM models like BERT, Roberta large on Asian hate dataset and achieved an F1 score of 84%.

PyTorchC++Distributed TrainingCommunicationMathematicsPython (Programming Language)

Zoho corporation

Machine Learning Engineer

Aug 2018 – Aug 2021 · 3 yrs · Chennai, Tamil Nadu · On-site

Built production AutoML framework from scratch using Bayesian optimization and genetic algorithms, deployed as distributed microservice handling 700K requests/hour. Implemented model-agnostic explainable AI using vectorized LIME and SHAP for local/global interpretability. Designed CI/CD pipelines for distributed model training, inference optimization, and metrics collection with 83% latency reduction through Redis caching.

JavaCode ReviewSystems DesignDistributed SystemsGenetic AlgorithmsDistributed Training+10

Amazon

Intern

Jan 2018 – Apr 2018 · 3 mos · Chennai, Tamil Nadu, India · On-site

Collaborated with Amazon’s “Kindle” team on the feature customer notification service to develop a REST API using the Coral framework along with SQS queue and EC2 compute.
Developed service alerted the employees through email and chat notification (backed by ELK stack).

JavaCommunicationElasticsearch