Eizen
Website:
eizen.ai
Company:
https://www.linkedin.com/company/eigenmaps
Seniority: Entry level
Industries: Software Development
Job details:
Full Stack Engineer — AI Applications
Product Engineering · React + TypeScript · Python + FastAPI · Agentic AI
Company: Eizen AI (Eigenmaps Private Limited)
Location: Bengaluru, India (On-site / Hybrid)
Experience: 3–5 years
Employment Type: Full-time
Function: Product & Platform Engineering
Reports To: Head of Engineering / Engineering Manager
About Eizen AI
Eizen AI is an applied AI company building computer vision, video intelligence, and agentic AI systems for enterprises. We work with Fortune 500 organisations across manufacturing, retail, healthcare, and robotics, turning real-world video and operational data into decisions that run in production — not in slide decks.
Our platform stack includes eizenOS, our video intelligence platform for large-scale perception and analytics, and eizenX, our agentic workflow design layer for building and orchestrating AI agents. Alongside these, our proprietary Dual Vision System combines ego-vision and exo-vision to give robotic and industrial systems a far richer operational understanding of their environment than single-viewpoint approaches allow.
Eizen operates from Hyderabad — our primary R&D centre — with a growing presence in Bengaluru and Atlanta, USA. We are a research-led team: our work sits at the intersection of self-supervised learning for video, visual symbol grounding, and production-grade AI engineering. The company was founded and is led by a PhD in Cognitive Robotics from IIT Kanpur, and our engineering culture reflects that — deep technical ownership, first-principles problem solving, and an insistence that research ideas survive contact with production.
About This Role
Eizen is expanding its engineering team to support a major client engagement focused on building and scaling AI products. You will own full-stack product modules end to end — React + TypeScript on the frontend, Python + FastAPI on the backend — and the agentic AI layer that sits between them.
This is a genuinely full-stack role with an AI centre of gravity. Agent orchestration, tool execution, and retrieval pipelines are not a side project here; they are the product. That brings engineering problems most web teams never encounter: long-running multi-step workflows, non-deterministic model output, partial failures mid-execution, streaming responses, and retrieval quality that has to be measured rather than assumed. You will design for those conditions across the stack — from the UI that streams a response to the worker that retries a failed tool call.
We are looking for an engineer who takes a module from architecture through production and stays accountable for it: contracts, data model, performance, tests, observability, and the go-get-things done behaviour.
What You'll Do
Frontend
• Build modern web applications using React, TypeScript, Next.js, and Tailwind CSS with clear feature modules, routing, reusable components, and design-system patterns.
• Implement real-time and streaming experiences using SSE and WebSockets for agent and LLM interactions.
• Implement state-management and caching strategies using React Query/SWR, Zustand, or Redux Toolkit.
• Drive frontend performance through code splitting, rendering optimisation, bundle analysis, Core Web Vitals, and Lighthouse profiling.
• Apply accessibility standards and consistent, responsive UI patterns across the product.
Backend & APIs
• Develop and operate production backend services using Python and FastAPI.
• Design robust REST APIs with clear contracts, versioning, pagination, authentication and session handling, validation, and standardised error handling.
• Implement BFF (Backend for Frontend) patterns to integrate frontend applications cleanly with backend and AI services.
• Integrate internal and external systems through REST APIs, third-party services, and microservice boundaries.
• Apply Python concurrency appropriately — asyncio, thread pools, process pools — with a clear view of the trade-offs.
Agentic AI & GenAI
• Design and build agentic AI and GenAI applications using LangGraph, LangChain, n8n, or comparable frameworks.
• Build AI agents, multi-step workflows, tool and function calling, and API integrations against OpenAI, Gemini, and Claude models.
• Build backend services for AI workflows covering orchestration, state management, tool execution, retries, timeouts, idempotency, and retrieval pipelines.
• Implement and tune RAG pipelines — embeddings, vector search, hybrid retrieval, and reranking — and measure retrieval quality rather than assume it.
• Apply prompt engineering as an engineering discipline: versioned, evaluated, and regression-tested.
Data & Databases
• Design data layers using PostgreSQL/MySQL — schema design, indexing, query optimisation, and performance tuning.
• Build ETL and data-processing pipelines using Databricks and PySpark where the workload calls for it.
• Use Redis for caching, distributed coordination, and rate limiting.
Distributed Systems, Performance & Reliability
• Apply distributed systems patterns including queues and workers, retries with exponential backoff, DLQs, rate limiting, circuit breakers, and backpressure.
• Profile and optimise backend services, asynchronous workloads, database queries, and API response times.
• Build production observability using structured logs, metrics, tracing, and monitoring.
• Troubleshoot performance, integration, and production issues, and lead root-cause analysis.
Testing, Delivery & Collaboration
• Own frontend and backend testing strategy using React Testing Library, Jest/Vitest, Pytest, and Playwright.
• Integrate component, API, integration, and E2E tests into CI/CD pipelines, and keep flaky failures under control.
• Work with Docker, Kubernetes, environment and configuration management, and automated build/test/deploy pipelines.
• Participate in architecture discussions, code reviews, and release activities in an Agile/Scrum setting.
• Collaborate with product, design, AI/ML, DevOps, and QA to take features from architecture through production.
Must-Have Skills
• 3–5 years of strong full-stack engineering experience with ownership of production applications.
• Strong production experience with React + TypeScript, including frontend architecture, refactoring, reusable components, and complex application development.
• Strong Python backend development experience, preferably with FastAPI.
• Experience designing and maintaining production REST APIs, including authentication, security, and third-party integration.
• Hands-on experience building AI/LLM or agentic applications — agent frameworks, tool/function calling, prompt engineering, or RAG pipelines.
• Strong knowledge of SQL and PostgreSQL/MySQL, including data modelling, indexing, and query optimisation.
• Strong understanding of Python concurrency — asyncio, thread pools, process pools — and the associated performance trade-offs.
• Experience with Tailwind CSS at scale, including reusable UI primitives and consistent design patterns.
• Strong testing experience with React Testing Library and Playwright, including CI integration and flaky-test debugging.
• Experience with frontend and backend performance profiling and optimisation.
• Understanding of distributed systems fundamentals — queues, workers, retries, resilience, and asynchronous processing.
• Experience with Git, Docker, environment management, deployment workflows, and CI/CD collaboration.
• Strong engineering fundamentals around maintainability, scalability, reliability, and production debugging.
Nice to Have
• Hands-on experience with LangGraph, LangChain, n8n, or similar orchestration frameworks.
• Experience with Next.js and BFF architecture in production.
• Experience with vector databases, hybrid search, and reranking.
• Experience with Databricks, PySpark, or large-scale data pipeline development.
• Experience with Kafka, RabbitMQ, AWS SQS, or similar messaging systems.
• Exposure to gRPC.
• Experience with Kubernetes and cloud platforms — AWS, Azure, or GCP.
• Experience with OpenTelemetry, Datadog, Prometheus, or similar observability platforms.
Education
Bachelor's or Master's degree in Computer Science, Information Technology, Engineering, or a related field preferred. Equivalent practical experience and a strong body of production work will be considered.
What Success Looks Like in the First Six Months
• You own one or more product modules end to end — frontend, API, data model, and AI workflow — and the team routes questions about them to you.
• Agent workflows behave predictably under failure: retries, timeouts, and idempotency are designed in rather than patched on.
• API contracts are stable and well-documented, and frontend integration no longer requires guesswork.
• Test coverage and CI signal are trusted, and flaky failures stop being background noise.
• Production issues are diagnosed from logs, metrics, and traces rather than reproduction attempts.
Why Join Eizen
• AI is the product. Agent orchestration, retrieval, and tool execution are the core of what we ship, not a wrapper around someone else's API.
• Real full-stack scope. Frontend architecture, backend services, data layer, and AI pipelines — you will work across all of it, not one slice.
• Enterprise stakes. Our platforms run in production for Fortune 500 clients across manufacturing, retail, healthcare, and robotics.
• Ownership from day one. Small, senior team. You will shape architecture and standards rather than inherit them.
How to Apply
Send your CV, along with a short note on a production system you have owned end to end — what you built, what broke, and what you changed as a result — to careers@eizen.ai.
Eizen AI is an equal opportunity employer. We evaluate applicants on capability and potential, and welcome candidates from all backgrounds.
Fill up the form: https://forms.office.com/r/y9JFDDEZqX
Click on Apply to know more.
