Sense Tech Stack

Conversational AI platform automating high-volume recruiting workflows

Software Development San Francisco, California 201–500 employees Founded 2016 Privately Held

Sense builds conversational AI into recruiting automation, combining chatbots, candidate matching, and talent CRM to compress hiring cycles. The stack reveals a modern AI-first architecture: LLM tools (LangChain, LlamaIndex, LLaMA, Gemini), vector databases (Pinecone, Chroma, FAISS), and LLM ops platforms (LangSmith, Arize AI) sit alongside Kafka/RabbitMQ for high-throughput messaging. Engineering-heavy hiring and a project backlog focused on conversational agents and ATS integrations signal active platform expansion, though pain points around integration reliability and implementation velocity suggest scaling friction.

Tech Stack 86 technologies

Core StackAsana Jira Salesforce Zendesk Python Flask MySQL AWS Datadog New Relic Kafka RabbitMQ Redis Slack 6sense Snowflake LangChain Pinecone Arize AI LangSmith CrewAI LangGraph Memcached Apollo LinkedIn Sales Navigator LlamaIndex LLaMA Gemini FAISS Chroma+54 more

What Sense Is Building

◆Challenges

Resolving technical debt
Integration platform scalability
Improving candidate experience
Integration reliability
Integration with applicant tracking systems
Timely go-live delivery
Implementation efficiency improvement
Customers can't figure problem out
Implementation time
Reducing latency issues

▲Active Projects

Optimizing high-throughput communication pipelines
New integrations and partner expansions
Configuring ai-driven workflows
Implementation velocity and operational efficiency
New sense customer implementations
Module implementations for existing customers
Integration with applicant tracking systems
Building conversational agents for recruiting
Designing automated intelligence for multi-turn interactions
Platform scalability and performance

Hiring Activity

Accelerating15 roles · 15 in 30d

Department

Engineering

Design

Data

Product

Ops

Sales

Support

Seniority

Lead

Mid

Senior

Junior

Company intelligence

Find more companies like Sense by tech stack, pain points and active projects

Get started free

About Sense

Sense is a conversational AI recruiting platform founded in 2016 and based in San Francisco. The product spans candidate engagement (chatbots, text messaging), talent management (CRM, campaigns, scoring), and operational automation (interview scheduling, referrals). Sense serves mid-market and enterprise talent teams—spanning healthcare, retail, logistics, and staffing—with a customer base of over 1,000 organizations. The platform operates across 201–500 employees with engineering, design, and data teams distributed between the US and India. Active implementation work and ATS integrations dominate the roadmap, reflecting a move toward deeper, wider applicant tracking system embeddings.

HeadquartersSan Francisco, California

Company Size201–500 employees

Founded2016

Hiring MarketsIndia, United States

Frequently Asked Questions

What is Sense's tech stack?

Sense uses Python, Flask, MySQL, and AWS for core infrastructure. The AI layer includes LangChain, LlamaIndex, LLaMA, Gemini, and vector stores (Pinecone, Chroma, FAISS). Messaging is handled by Kafka and RabbitMQ. Observability relies on Datadog, New Relic, and Arize AI for LLM monitoring.

What is Sense working on?

Current projects include optimizing high-throughput communication pipelines, building conversational agents for recruiting, configuring AI-driven workflows, improving ATS integrations, and addressing platform scalability and latency issues.

Similar Companies in Software Development

Other companies in the same industry, closest in size

How this profile is built

Sense's technology stack, projects, and hiring signals are inferred from public hiring and company data — career pages, public listings, and company web presence — then clustered and de-duplicated. Figures are estimates that refresh over time. Read our full methodology →

This is not an official vendor or customer list. It is a technology-adoption signal inferred from public data, intended for B2B research.