Trail is the context layer AI agents run on.

We're building the missing layer between your company's rules, exceptions, and institutional knowledge and the agents trying to act on them. It's a governed graph that lets any agent or platform, including Trail agents, make the right call on your most complex business processes. Agents today fail not because models are weak, but because they're never given the judgment a business builds up over years. We're fixing that.

Learn more about what we're building here :
Youtube
Hugging Face
Trail
Nanonets Research

About the Role:

As a Principal SDE, you will architect and build scalable systems across Golang backend and React frontend, working on integrations, ML/AI APIs, complex workflows, and product capabilities. You’ll tackle challenging problems across system design, performance, and scalability, helping build infrastructure that processes hundreds of millions of documents monthly.

What we expect from you:
7+ years of experience
Agility in shipping features
Good at code design and architecture
Outstanding communication
Backend experience - Preferably golang, python
Databases - Understanding of data modeling for Nosql preferably cassandra.
Strong fundamentals in OOP design patterns.
Basic understanding of Devops.




Curiosity and Willingness to learn new things while solving a challenging problem.
Learning and incorporating best practices in software development, security and design/architecture.

Some of the engaging features we have shipped in backend:
Compile python code into C which could be imported into golang and then shipped as binary for on premise systems
Autoscale GPU dependent services with kubernetes with a custom metric
Displaying machine learning metrics in simplified ways to end users so they can act based on those metrics
Building large number and variety of integrations with relatively generic interface like salesforce, quickbooks, RPA's, external databases
Process large number of files in highly distributed manner in golang
Intelligent lookups leveraging vector databases with data synced from ERP Systems

Some of the interesting things we have shipped in frontend:
Ability for users to annotate documents so AI can learn which fields to extract.
Displaying machine learning metrics in simplified ways to end users so they can act based on those metrics
Letting users build complex visual workflows around our API in our product.
Let users visualize complex ML metrics in a very easy and intuitive way

📌 Principal Software Engineer Bengaluru
🏢 Trail
📍 Bengaluru