Portfolio
Selected work across our three businesses.
Key
How to read this portfolio
A current business does not mean every project is deployed. Each project record states its own stage, and results appear only where evidence supports them.
- ProjectProject record
- Specific work published by the founders: the problem, our contribution, the solution, the technologies and its current stage. Client names appear only with approval; results only with evidence.
- Capability overviewCapability overview
- What Smriti engineers in a family of work and how such systems are typically shaped. Not a case study: no customers, no results.
Project stages
- Stage: In development
- Being designed or built; not yet in use.
- Stage: Pilot
- In limited use to test whether it works for the task.
- Stage: Deployed
- In use in the environment it was built for.
- Stage: Internal platform
- Built for, and used in, our own engineering work.
- Stage: Research
- Exploratory work on a technical question; not a product.
Lead commercial business
Enterprise AI Platforms
Scalable AI products and agentic platforms for businesses in India, built on Google Cloud and AWS, alongside our own voice models and AI harnesses.
Explore Enterprise AI- Capability overview
Gemini-powered enterprise agents
Agents that work with an organisation's own knowledge and software, built on Google Cloud with Gemini models, Gemini Enterprise and the Agent Development Kit.
Technologies: Google Cloud · Gemini models · Gemini Enterprise · Agent Development Kit (ADK)
- Capability overview
Amazon Bedrock-based business platforms
Business platforms on AWS that combine foundation models available through Amazon Bedrock with an organisation's knowledge, tools and workflows.
Technologies: AWS · Amazon Bedrock
- Capability overview
Smriti voice models and applications
Voice-enabled systems that combine Smriti's own voice-model development with speech applications and, where relevant, third-party speech services.
Technologies: Smriti voice models · Cloud Text-to-Speech · Cloud Speech-to-Text
- Capability overview
AI harnesses and evaluation systems
The engineering around a model that makes it dependable: context handling, orchestration, tool integration, retrieval, workflow rules, evaluation and deployment logic.
Technologies: Model-agnostic · Google Cloud · AWS
Current business
Automotive Intelligence
Design, testing and refinement of ADAS solutions based on NVIDIA Hyperion and relevant NVIDIA DRIVE technologies, for Indian automotive applications.
Explore Automotive- Capability overview
NVIDIA Hyperion-based ADAS engineering
Design, testing and refinement of ADAS solutions built around NVIDIA Hyperion and relevant NVIDIA DRIVE technologies, for Indian automotive applications.
Typical use cases
- Adapting ADAS functions to intended operating conditions
- Evaluating system behaviour and documenting limitations
- Refining models and software from test evidence
Technologies: NVIDIA Hyperion · NVIDIA DRIVE
Current business
Accelerated Inference
Engineering of NVIDIA GPU-based inference systems: model deployment, serving and performance optimisation for AI applications.
Explore Inference- Capability overview
NVIDIA GPU inference systems
Model deployment, serving and performance engineering on NVIDIA GPU-based systems, shaped around what the application needs.
Typical use cases
- Deploying and serving models for an AI application
- Understanding workload behaviour under realistic traffic
- Optimising response time and throughput against cost and quality
Technologies: NVIDIA GPUs
Project records are added as work is approved for publication. Diagrams on capability overviews are reference architectures — the typical shape of a system, not a specific deployment. Read more about how we work.
Work with us