About the role
Full-Stack AI Engineer.
2+ years experience | Chennai / Bangalore
About the Role
We are seeking a high-velocity, product-minded Full-Stack AI Engineer with 2–3 years of professional
software engineering experience to join our team. In this role, you will bridge the gap between robust
web architecture and cutting-edge artificial intelligence. You will not just be connecting APIs; you will be
building production-grade, stateful AI agents, optimizing Retrieval-Augmented Generation (RAG) pipelines,
and crafting seamless, intuitive user experiences using React and Python.
Key Responsibilities.
AI Integration & Orchestration: Design, build, and deploy agentic workflows and multi-agent systems
using framework layers like LangChain, LangGraph, or LlamaIndex.
Backend Development: Develop high-performance, asynchronous RESTful and WebSocket APIs in
Python (via FastAPI or Django) to handle heavy AI inference workloads.
Frontend Engineering: Build responsive, real-time user interfaces using React.js and TypeScript(or
Next.js) tailored for dynamic AI interactions (e.g., streaming chats, multi-modal dashboards, and
interactive visual data blocks).
Data & Vector Management: Structure and optimize vector databases (ChromaDB, Pinecone, or
pgvector) for lightning-fast, context-aware semantic search.
Evaluation & Optimization: Fine-tune system prompts, implement guardrails, minimize token latency, and
implement robust evaluation metrics (using tools like LangSmith or Phoenix) to monitor AI accuracy and
drift.
Agile AI Workflows: Utilize modern AI-native coding setups (such as Cursor, GitHub Copilot, or Claude
Code) to accelerate feature shipping and maintain a rapid deployment cycle.
Required Technical Skills.
Frontend: React.js, TypeScript, Next.js, HTML5/CSS3, TailwindCSS, State Management (Zustand, Redux, or
React Context).
Backend: Python 3.x, FastAPI, Flask, or Django; asynchronous programming (asyncio).
AI / LLM Ecosystem: Deep hands-on experience calling foundational models (OpenAI, Anthropic Claude,
Google Gemini) and open-weight models (Llama, Mistral) through managed APIs or hosting layers.
Vector Architecture: Foundational knowledge of embeddings, semantic chunking strategy, and vector index
operations.
Database & DevOps: PostgreSQL or MongoDB; Containerization using Docker; Familiarity with cloud
platforms (AWS, GCP, or Azure) and basic CI/CD engineering pipeline
Good to Have (Preferred Qualifications).
Experience with the Model Context Protocol (MCP) or agent frameworks like CrewAI or AutoGen.
Exposure to fine-tuning (LoRA/PEFT) or self-hosting open-weight models (vLLM, Ollama).
Advanced retrieval techniques such as hybrid search and reranking.
Evaluation tools like RAGAS or DeepEval, and awareness of LLM security risks such as prompt injection.
Kubernetes, background job queues (Celery, Redis), or the Vercel AI SDK.
A portfolio or GitHub projects showing shipped AI applications
This page is fully interactive when JavaScript is enabled. Please enable JavaScript to apply or browse related roles.
