Generative AI Engineer

Company Description

Sastra Innovations (OPC) Private Limited is building enterprise AI products for document-heavy workflows.

Our product stack includes:

• Medha
  • proprietary AI reasoning and intelligence layer
• MedhaOS
  • governance, orchestration, policy, RBAC, audit, approvals, and control layer
• SastraPDF
  • document intelligence and workflow execution layer

We have completed private alpha validation and are preparing for beta restart, enterprise design partners, and paid pilots.

Role Description

We are looking for a Generative AI Engineer who wants to work on applied enterprise AI, document intelligence, and agentic workflows.

This is not a generic chatbot role. You will work on systems that need to understand documents, reason across context, support workflow actions, and operate within governance, privacy, and access-control boundaries.

What You Will Build

You will work on:

• Document Intelligence
• Enterprise AI Governance
• Agentic AI workflows and orchestration
• Multi-model AI orchestration
• Persistent AI memory and contextual reasoning
• Enterprise workflow automation
• AI safety and policy enforcement
• Production-scale AI systems

Responsibilities

• Build and improve AI workflows for document understanding, extraction, summarization, comparison, review, and action support
• Work with LLMs, RAG pipelines, embeddings, vector databases, OCR pipelines, and agentic workflows
• Integrate AI capabilities with product APIs, backend services, and document-processing pipelines
• Build governance-aware AI capabilities including RBAC, policy enforcement, approvals, auditability, and human-in-the-loop flows
• Help design evaluation methods for accuracy, reliability, latency, cost, observability, and safety
• Collaborate closely with the founding team on product architecture and implementation
• Write clean, readable, maintainable code and document important technical decisions
• Write meaningful tests and participate in code reviews
• Contribute to platform design, performance, scalability, reliability, and security

Technology Stack

• Python
• FastAPI
• PostgreSQL
• Redis
• REST APIs
• Git
• Docker
• RAG
• Vector databases
• OCR / document processing
• LangChain / LlamaIndex is a plus
• MCP and agentic AI experience is a plus
• Cloud, Kubernetes, or MLOps exposure is a plus

Good Fit

• Strong Python skills
• Practical experience with LLMs, RAG, embeddings, NLP, backend systems, or document AI
• Familiarity with APIs, databases, and production software engineering
• Understanding of prompt engineering, model evaluation, and AI workflow design
• Interest in enterprise AI, governance, privacy, and production-grade systems
• Ability to learn fast and work with high ownership in an early-stage product environment
• Clean coding habits, Git discipline, testing mindset, and willingness to improve engineering practices

Experience

We care more about what you have built than the number of years on your resume.

Ideal:

• 2–6 years building AI, backend, ML, or product engineering systems
• Exceptional fresh graduates with strong projects are encouraged to apply
• Startup or product-building experience is a strong advantage

What We Value

• Ownership over titles
• Curiosity over credentials
• Product thinking over feature delivery
• Simplicity over unnecessary complexity
• Clean and maintainable code
• Ability to solve hard engineering problems
• Strong communication
• Comfort working closely with founders in an early-stage environment

Location

Hyderabad preferred. Hybrid or remote flexibility can be discussed for the right candidate.

Engagement

This is a full-time role. Engagement details can be discussed based on fit, skill level, and commitment.

Compensation

Competitive and based on experience, capability, and overall fit.

Interview Process

• Resume / profile screening

• Technical discussion

• Practical coding or architecture discussion

• Founder interaction