Backend AI Engineer
Description
This position is listed on behalf of a partner company, which manages all applications and next steps. Our partner is looking for a Backend AI Engineer based in India .
This role offers an opportunity to build the core interfaces and backend services powering an enterprise-grade AgenticOps platform. You will connect real-time operator experiences with asynchronous AI agents, making complex reasoning processes, network activity and automated remediation workflows accessible and manageable. Working across frontend architecture, backend-for-frontend services and modern AI frameworks, you will help create reliable tools for IT and security operations teams. A major focus will be delivering responsive visualizations, low-latency streaming and secure human-in-the-loop controls for autonomous systems. You will also integrate advanced model-serving technologies and open-source automation tools into a cohesive platform. This position is suited to a senior engineer who combines deep full-stack expertise with practical experience building AI-native applications.
Accountabilities
-
Design and develop the primary AgenticOps operator console, including real-time telemetry, interactive multi-agent reasoning traces, execution dry-runs and human-in-the-loop approval and override controls.
-
Build high-performance dynamic topology and directed acyclic graph (DAG) visualizations to represent enterprise network maps, asset dependencies and live multi-agent execution flows.
-
Optimize canvas, SVG and WebGL-based interfaces to render large-scale network structures and complex reasoning graphs smoothly and without performance bottlenecks.
-
Engineer bidirectional, low-latency streaming pipelines using WebSockets, Server-Sent Events (SSE) and other relevant protocols to deliver agent activity, tool invocation data and live terminal output.
-
Develop backend-for-frontend (BFF) services and edge middleware using Go, Python with FastAPI, or TypeScript.
-
Implement secure session-state persistence, token caching, SAML/OIDC authentication and fine-grained role-based access control (RBAC).
-
Integrate frontend and backend services with agent runtimes, open-source automation tools and AI model endpoints, including NVIDIA NIMs, vLLM and local small language models.
-
Build intuitive interfaces for autonomous systems, incorporating progressive disclosure of reasoning, confidence and risk scoring, before-and-after change previews and safety-critical confirmation workflows.
-
Apply AI-assisted software development practices, including automated component scaffolding, synthetic UI testing and continuous evaluation pipelines, to improve engineering productivity and delivery quality.
-
Collaborate across engineering and platform teams to connect modern AI frameworks, infrastructure integrations and open-source technologies into a reliable enterprise solution.
Requirements:
-
Experience: At least 8 years of experience building enterprise-grade full-stack web applications, including at least 3 years focused on AI/LLM-native interfaces, observability platforms (APM/SIEM) or network operations tooling.
-
Frontend engineering: Advanced proficiency in TypeScript, React or Next.js, and Tailwind CSS.
-
State management: Hands-on experience with Zustand and TanStack Query, including managing complex application state and real-time data updates.
-
Rendering and visualization: Production experience with at least one of React Flow, Cytoscape.js, PixiJS or D3.js, using canvas, SVG or WebGL technologies.
-
Graph interfaces: Ability to build and optimize large hierarchical graphs, network topologies and multi-step agent reasoning trees.
-
Real-time communication: Strong experience with SSE, WebSockets and chunked streaming, including partial token rendering and optimistic UI updates under network latency.
-
Backend and BFF development: Experience building backend-for-frontend services using Go, Python with FastAPI, or TypeScript.
-
Security and authentication: Practical knowledge of SAML/OIDC authentication, RBAC, session-state management and token caching.
-
AI and agent frameworks: Hands-on experience with at least one of LangChain, LangGraph or Vercel AI SDK, as well as consuming model endpoints powered by NVIDIA NIMs, vLLM or Ollama.
-
UX for autonomous systems: Strong understanding of user experience design for non-deterministic software, including human-in-the-loop approval and override processes, progressive reasoning disclosure, confidence and risk indicators, change previews and safety-critical confirmations.
-
Preferred additional experience:
-
Familiarity with gRPC-Web.
-
Experience with OpenClaw or Browser-Use.
-
Knowledge of local small language model (SLM) deployment.
-
Exposure to NVIDIA or Cisco platform integrations.
-
Experience applying AI-assisted software development practices, including component scaffolding, synthetic UI testing and continuous evaluation pipelines.
-
Strong problem-solving skills and the ability to balance frontend performance, backend reliability, security and usability in complex enterprise applications.
Benefits:
-
Fully remote working arrangement.
-
Full-time employment opportunity.
-
Opportunity to work on an enterprise AgenticOps platform combining AI agents, real-time infrastructure visualization and automated operations.
-
Exposure to modern AI frameworks, model-serving technologies and open-source agentic tools.
-
Opportunity to contribute to advanced solutions for IT and security operations.