ApplySarthi

Lead Fullstack AI Engineer

Jobgether

Tailor my CV for this job, freeView job and applyYour CV rewritten for this role, from your real experience. Sign in with Google, nothing to install.

Got this interview? Our apps help you get the job.

Skills named in this job

Read from the description itself, not inferred.

This role on the market

898 open fullstack roles across 176 companies are on ApplySarthi right now, most of them in Bengaluru (23), Hyderabad (16), Delhi NCR (4).

What fullstack roles keep asking for: React (32%), TypeScript (25%), Java (19%), Agile (17%), JavaScript (16%), Python (16%), CI/CD (15%), Docker (15%) — counted across their open postings here.

CSS jobs · FastAPI jobs · Go jobs · LLMs jobs

Jobgether has 4,317 open roles listed here.

Counted across 14 company job boards, updated as roles open and close.

Preparing for this interview

Interviews for fullstack roles keep coming back to React, TypeScript, Java, Agile. Practise those questions before you sit with Jobgether.

Questions you are likely to be asked

  1. Why do you want to join Jobgether?
  2. What is your experience with LangChain? Tell me one thing you learned the hard way.
  3. How did you know your model was actually good, and not just good on your test set?
  4. Tell me about a time the data was messy or wrong. What did you do?
  5. How would you explain your model's result to someone who is not technical?

Prep Sarthi gives you a free mock interview: an AI interviewer asks you questions like these out loud, from your own CV and this job, and shows your score and your weakest answer.

Practise the Lead Fullstack AI Engineer at Jobgether interview free →

Accountabilities:: Operator Cockpit and Human-in-the-Loop (HITL) Controls: Design and develop the primary AgenticOps operator console, providing real-time telemetry streaming, interactive multi-agent reasoning traces, execution previews, and human approval or override capabilities. Build intuitive interfaces that allow IT and SOC operators to monitor, understand, and control autonomous AI-driven processes. Dynamic Topology and Graph Visualization: Develop high-performance interactive visualizations using WebGL, Canvas, SVG, or related technologies to display large-scale enterprise network maps, asset dependencies, and live multi-agent execution graphs. Optimize rendering performance to ensure smooth interaction with complex hierarchical graphs and dynamic data structures. Real-Time Streaming Infrastructure: Engineer low-latency, bidirectional communication systems using WebSockets, Server-Sent Events (SSE), and gRPC-Web to support real-time agent updates, tool invocation payloads, and terminal outputs. Implement efficient streaming interfaces capable of handling partial AI-generated responses, asynchronous events, and changing network conditions. Backend-for-Frontend (BFF) Development: Design and build scalable backend-for-frontend services using Go, Python (FastAPI), or TypeScript. Implement session persistence, token caching, SAML/OIDC authentication, and fine-grained Role-Based Access Control (RBAC) to ensure secure and reliable application experiences. AI and Agent Ecosystem Integration: Connect frontend applications with AI agent runtimes, open-source automation frameworks, and model-serving infrastructure. Integrate tools and services such as LangChain, LangGraph, Vercel AI SDK, OpenClaw, Browser-Use, NVIDIA NIMs, vLLM, and local Small Language Models (SLMs). Ensure seamless communication between user interfaces, autonomous agents, AI models, and enterprise technology platforms. User Experience for Autonomous Systems: Develop intuitive user experiences for non-deterministic AI workflows, incorporating progressive disclosure of agent reasoning, confidence and risk scoring, before-and-after change previews, and safety-critical confirmation processes. Ensure operators have sufficient visibility and control over automated actions, including the ability to review, approve, or override execution steps. AI-Augmented Software Development: Integrate AI-assisted development practices into the software development lifecycle, including automated component scaffolding, synthetic UI testing, and continuous evaluation pipelines. Leverage emerging AI development tools to accelerate engineering workflows, improve software quality, and streamline product delivery. Collaborate with cross-functional engineering and product teams to deliver reliable, scalable, and high-performance enterprise solutions. Requirements: At least 8 years of professional experience developing enterprise-grade full-stack web applications. Minimum 3 years of experience working on AI/LLM-native interfaces, observability platforms such as Application Performance Monitoring (APM) or Security Information and Event Management (SIEM), or network operations tooling. Frontend Development: Advanced proficiency in TypeScript, React, Next.js, and Tailwind CSS, with strong knowledge of modern frontend architecture and application development. Experience with state management solutions such as Zustand and TanStack Query. Strong understanding of rendering optimization and frontend performance techniques for applications handling real-time streaming data. Graph and Visualization Technologies: Production experience with at least one of the following visualization libraries: React Flow, Cytoscape.js, PixiJS, or D3.js. Proven ability to develop and optimize Canvas, SVG, or WebGL-based interfaces for large-scale hierarchical graphs, network topologies, and multi-step agent reasoning trees. Real-Time Communication and Streaming: Strong practical experience with Server-Sent Events (SSE), WebSockets, and chunked streaming protocols. Understanding of partial token rendering, asynchronous data handling, optimistic UI updates, and performance management under network latency. Backend and BFF Architecture: Experience developing backend-for-frontend services using Go, Python (FastAPI), or TypeScript. Knowledge of authentication and authorization technologies, including SAML, OIDC, and fine-grained Role-Based Access Control (RBAC). Practical experience with session state persistence, token caching, and secure application architecture. AI and Agentic Technologies: Hands-on experience with modern AI agent frameworks such as LangChain, LangGraph, or Vercel AI SDK. Experience integrating and consuming model endpoints powered by NVIDIA NIMs, vLLM, or Ollama. Understanding of agent-based architectures, AI-powered automation, and integration between frontend applications and autonomous AI systems. UX for Autonomous Systems: Strong product and design intuition for developing interfaces around non-deterministic AI behavior. Experience implementing human-in-the-loop approval and override workflows, progressive disclosure of AI reasoning, confidence and risk indicators, change previews, and safety-critical confirmation mechanisms. Strong analytical and problem-solving skills, with the ability to translate complex technical requirements into reliable and intuitive user experiences. Excellent communication and collaboration skills, with the ability to work independently and contribute to technical decision-making. Additional Advantages: Experience with gRPC-Web and advanced real-time communication architectures. Familiarity with open-source agentic tools such as OpenClaw and Browser-Use. Experience deploying or integrating locally hosted Small Language Models (SLMs). Previous experience integrating NVIDIA or Cisco platforms and technologies. Familiarity with AI-assisted software development workflows, including automated component generation, synthetic UI testing, and continuous evaluation pipelines. Experience building enterprise cybersecurity, network operations, or IT automation platforms. Benefits: Fully remote working arrangement, offering flexibility to work from anywhere in India. Full-time employment opportunity within the IT services and artificial intelligence sector. Opportunity to lead the development of an advanced enterprise AgenticOps platform. Hands-on exposure to cutting-edge AI technologies, autonomous agents, and large language model ecosystems. Opportunity to work with modern engineering frameworks, including React, Next.js, LangChain, LangGraph, NVIDIA NIMs, and vLLM. Exposure to enterprise-scale cybersecurity, network infrastructure, observability, and IT automation challenges. Significant technical ownership and influence over application architecture and engineering decisions. Opportunity to work on complex, high-performance systems involving real-time streaming, graph visualization, and intelligent automation. Professional development through continuous exposure to emerging AI technologies and innovative engineering practices.

Match this job to your CV

ApplySarthi scores your CV against this role, shows the skills you are missing, and writes a tailored version for the application.

Check my match →

Similar open roles

Need answers during your interview? Try Live Sarthi.

Live Sarthi, an Interview Sarthi app, shows answer suggestions during the call.

Try Live Sarthi free →

A Windows app, from the same team as ApplySarthi.

Listed on lever · posted 2026-11-17. ApplySarthi collects openings and links to application pages; the role is advertised by Jobgether, not by us.