Lead – AI Platform

Location: Hyderabad (On-site) Full Time Department: R& D Engineering Reports To: Head of Engineering / CTO Office Timings: 12PM - 9PM Position Overview We are hiring a technically hands-on Senior Architect to lead the design, development, and deployment of a modular AI-driven automation platform, integrating AI Agent framework, Rag Model solution, Large Language Models (LLMs), Machine Learning and rule-based automation engines. This platform will power intelligent workflow automation across internal operations, customer service, and enterprise integrations, enabling our clients to achieve hyper-productivity and reduce operational costs. Primary Responsibilities Architecture & Framework Engineering - Architect an extensible, component-based automation framework capable of: - Custom AI Agent Framework - Pluggable ML/LLM pipelines - Custom event triggers and action processors - Event-driven workflows with state persistence - Build core execution capabilities such as: - Workflow DAG handling - Task queues and async job coordination - Error handling, checkpointing, and retries - Define reusable microservice APIs and developer-facing SDKs - Design scalable multi-tenant architecture for horizontal scaling AI/LLM Integration - Implement LLM abstraction layers using LangChain, Semantic Kernel, or similar libraries - Integrate open and commercial LLMs such as OpenAI, Claude, Mistral, or Cohere - Build Retrieval-Augmented Generation (RAG) pipelines using vector stores like Pinecone, Qdrant, or FAISS - Develop components for: - Prompt templates - Context memory - Chaining and orchestration of multi-step agents Platform Engineering - Containerize services using Docker and orchestrate with Kubernetes and Helm - Build and maintain CI/CD pipelines using Azure DevOps, GitHub Actions, or Argo - Implement scalable infrastructure patterns including autoscaling and service mesh networking - Setup observability stack including structured logs, metrics, tracing, and alerting UI/UX Enablement - Enable low-code/no-code interfaces through backend schema-driven UI renderers - Collaborate with React + TypeScript frontend engineers to build: - Visual workflow builders - Monitoring dashboards - Ensure responsiveness and performance of UI for synchronous and long-running processes Leadership & Collaboration - Lead and mentor a cross-functional team of engineers - Establish engineering best practices across design, coding, testing, and performance optimization - Facilitate cross-team alignment with data scientists, DevOps, and product managers - Support hiring efforts and technical onboarding Minimum Qualifications - Bachelor’s or master’s in computer science, Engineering, or related field Preferred Technical Skills - AI/LLM Technologies: OpenAI, Claude, Cohere, HuggingFace Transformers, LangChain, Semantic Kernel, Haystack, - Vector databases: Pinecone, FAISS, Qdrant - Workflow & Orchestration: Temporal, n8n, Redis Streams, RabbitMQ, Celery, Kafka, EventBridge - Backend & Platform: Python, Node.js, RESTful APIs, gRPC, Webhooks, Kubernetes, Docker, Cloud platforms Azure App Services, AWS Lambda, GCP Cloud Run - DevOps & Observability: GitHub Actions, Azure DevOps, Grafana, Loki, OpenTelemetry - Frontend (for UI integration): React, TypeScript, Redux, TailwindCSS or Material UI Soft Skills - Strong communicator with documentation and architectural diagramming proficiency - Collaborative mindset with a focus on mentorship, code quality, and engineering velocity - Adaptability to rapidly evolving AI/LLM ecosystem Why Join Us - Build a flagship AI automation platform from the ground up - Work with a visionary Founder, solving real-world enterprise automation challenges Influence technical strategy, product direction, and scaling decisions