Website:
workfabric.com
Job details:
At Workfabric AI, we are a fast-paced start-up building foundational infrastructure for the enterprise AI era. We believe context is every organization’s competitive advantage — and the companies that harness it will win in the AI era.
On this journey, Workfabric AI is building ContextFabric — the context backbone for enterprise AI Agents. Most of how teams actually work never makes it into systems of record: the workflows, judgements, and cross-app sequences that drive real business outcomes stay invisible to AI. ContextFabric captures that missing layer and feeds it to AI Agents, so they can take the right actions, handle exceptions, and work reliably in production.
ContextFabric consists of three components: Context Sensors capture how work actually unfolds across your applications — no integrations required; the Context Cloud organizes those signals into a living, governed enterprise context backbone; and the Context Orchestrator delivers the right context to agents at the moment of execution. The result: 60% faster task completion, 90% lower compute spend, and 70% fewer hallucinations.
Workfabric AI has offices in Boston, MA, Palo Alto, CA, and Bangalore, India, with a growing roster of enterprise customers.
About the role
We're looking for a Senior Engineer to design, build, and scale the platform powering our next-generation AI twins— the services that let them plan, reason, and act at production scale.
This role sits at the foundation: the services that let agents plan, reason, and act at production scale, and the cloud infrastructure they run on. You'll work end to end — shaping the problem, designing the architecture, writing the code, and operating it in production. You'll set patterns others build on, and you'll be directly accountable for the systems that ship.
What you'll be doing
- Design and build the platform services behind our next-generation AI twins — the loops that plan, reason, evaluate, and act on an objective, from problem framing through production.
- Own the cloud infrastructure these systems run on: container orchestration, deployment, autoscaling, cost, and reliability — provisioned as infrastructure-as-code.
- Build and maintain automated CI/CD pipelines, including reusable templates, so the team ships safely and often.
- Develop data ingestion, retrieval, and storage layers — including vector stores — that ground agent reasoning in real source material.
- Implement session and state management for conversation history, checkpointing, and recovery across long-running agent runs.
- Build event streaming and messaging for real-time progress, and instrument everything with logging, metrics, and tracing.
- Design authentication and identity across the platform, and partner with security on access controls and approval workflows for agent operations.
- Help set engineering patterns and quality standards for your area, and support the engineers around you through code review and pairing.
Who you are
What we need to see
- B.E. / B. Tech from a top university in India in one of the following departments (i) Computer Science, (ii) Information Sciences, (iii) Information Technology
- Minimum 5+ years building production software with Python, with strong backend fundamentals in API design and data modeling.
- Primary, hands-on experience building services with FastAPI.
- At least 1+ year of that experience hands-on with LangChain, building LLM-backed applications.
- Experience deploying and operating services in the cloud, and the appetite to own the infrastructure your systems run on.
- A track record of owning features or services end to end, from design through production.
- Clear communication and the ability to work autonomously in an ambiguous, fast-moving space.
Good to have
- Experience with React for building developer-facing UIs and dashboards.
- Infrastructure-as-code with Terraform.
- Kubernetes and Helm for deployment.
- Hands-on work with agent frameworks, RAG, and vector databases.
- Observability — structured logging, distributed tracing, and metrics.
Why join us
- Real ownership — Lead a core surface of the product from day one, with the autonomy to make decisions that stick.
- Hard problems — Work at the frontier of autonomous reasoning, where the right answer isn't in a textbook yet.
- Modern tooling — A clean, modern codebase and the freedom to pick the right tool for the job.
- Room to grow — A small, senior team where your patterns become the standard and your scope expands with the product.
- Direct impact — Ship to real users on a short cycle and watch what you build change how work gets done.
Click on Apply to know more.