Looking for a job

Sudhanshu Passi

@sudhanshupassi

Message

I build low-latency AI platforms, RAG pipelines, and real-time product backends from concept to scale.

India

Message

What I'm looking for

I'm looking to build user-centric AI products from concept to scale, especially low-latency AI backends, RAG systems, real-time streaming platforms, and autonomous agent workflows.

I've built production-grade AI platforms across e-commerce, HR tech, and consumer AI at Embedia Independent AI Ventures, taking products from concept to market as a Lead AI Architect.

I engineered multi-agent AI backends, real-time APIs, PostgreSQL RAG pipelines, and streaming voice interfaces that delivered under-200ms conversational responses and sub-500ms voice latency. I also improved demand forecast accuracy by 50% through neural-network-powered data systems and automated market research and catalog creation with autonomous multimodal AI agents.

Previously at Vue.ai, I led the migration of 60+ AI-related microservices to Kubernetes and re-architected core data ingestion to reduce response times below 200ms. At Locale.ai, I built a high-throughput geospatial ingestion pipeline processing 5,000+ requests per second and helped launch a logistics analysis platform from scratch.

At CoWrks, I built core authentication, booking, social, and messaging services, delivered investor-facing AI/ML prototypes, and pioneered CI/CD automation for 20+ microservices. I enjoy bridging deep technical execution with user-centric product design while mentoring engineers into independent owners.

Experience

Work history, roles, and key accomplishments

Current

Lead AI Architect

Current

Independent AI Ventures

Jan 2022 - Present (4 years 8 months)

• Delivered <200ms conversational AI responses by engineering a multi-agent backend with a real-time API, dynamic orchestrator, and PostgreSQL RAG pipeline.
• Achieved seamless sub-500ms voice latencies by architecting real-time streaming interfaces using open-source voice models and ElevenLabs for an automated HR interviewing platform.
• Increased demand forecast accuracy by 50% by engineering

PyTorch fastAPI PostgreSQL Kafka Redis Docker Kubernetes AI Agents ElevenLabs RAG Multi agent orchestration

Senior Backend Engineer

Vue.ai

Jan 2021 - Jan 2022 (1 year)

• Enhanced reliability and uptime for a high-volume enterprise production environment by leading a migration of 60+ AI-related microservices to Kubernetes.
• Cut response times to <200ms and significantly increased platform flexibility by re-architecting the core data ingestion service for the platform.

Lead Backend Engineer

Locale.ai

Jul 2019 - Jan 2020 (6 months)

• Enabled clients to build real-time geolocation dashboards of any city by architecting and building a logistics analysis platform from scratch in close collaboration with product and design.
• Processed 5,000+ req/sec from raw data into queryable geospatial data by building a high-throughput ingestion pipeline as the core data backbone.
• Uncovered critical insights like supply bottlenecks and

Backend Engineer

CoWrks

Jun 2017 - Jul 2019 (2 years 1 month)

• Supported a tech team scaling from 8 to 60 by architecting and building keystone services (authentication, booking, social network, messaging).
• Secured a successful fundraising round by delivering investor-facing AI/ML prototypes (facial recognition, CCTV analysis) presented by the CTO.
• Boosted developer velocity and stability by pioneering the company’s first CI/CD pipeline (Jenkins), aut