Senior Full Stack Engineer (Python / AI Platforms)

Marktine Technology Solutions Pvt. Ltd.; Jaipur; On-site; INR 2,500,000 - 4,500,000; Full time

Job summary

Vriti in Jaipur seeks a senior backend engineer with 6–7+ years of Python experience to architect and deliver AI-enabled systems. You will design production-grade RAG pipelines, integrate LLM orchestrations, and build high-throughput APIs.

Expertise with vector databases and modern frontend stacks is valued for seamless end-to-end delivery. Join a data-driven team that values scalable architecture, performance, and mentorship of junior engineers.

Qualifications

• 6–7+ years in full-stack Python development.
• Proficiency in Python and asynchronous frameworks.
• Production experience with RAG pipelines and semantic search.
• Strong frontend experience with React/TypeScript.
• Hands-on with vector databases and PostgreSQL.

Responsibilities

• Architect and deploy production-grade RAG pipelines with chunking, multi-vector indexing, re-ranking, and context window optimization.
• Integrate and evaluate LLM orchestrations using LangChain, LlamaIndex, or custom workflows.
• Design and optimize RESTful and WebSocket APIs using FastAPI or DRF.
• Manage vector databases (Pinecone, Milvus, Qdrant, ChromaDB, pgvector) for retrieval and storage.

Skills

Python

FastAPI/DRF

RAG/GenAI

React/TypeScript

Vector DBs

PostgreSQL

System Design

API Security

Git & Docker

CI/CD & Cloud

Mentoring

Job description

Key Responsibilities

• Backend & AI Systems Architecture
  • Architect, implement, and deploy production-grade RAG pipelines incorporating intelligent chunking strategies, multi-vector indexing, re-ranking, and context window optimization.
  • Integrate and evaluate LLM orchestrations using frameworks such as LangChain, LlamaIndex, or custom agentic workflows.
  • Design, build, and optimize high-throughput, low-latency RESTful and WebSocket APIs using FastAPI or Django REST Framework (DRF).
  • Manage vector databases (e.g., Pinecone, Milvus, Qdrant, ChromaDB, or pgvector) for hybrid retrieval, embedding storage, and similarity search.
• Full Stack & Frontend Delivery
  • Build modular, responsive, and data-dense web interfaces using modern frontend frameworks (React.js, Next.js, or Vue.js).
  • Implement state management, streaming chat completions (Server-Sent Events / WebSockets), and data visualization components.
  • Ensure seamless data contract integration between frontend interfaces and AI-driven backend microservices.
• Data Modeling, Performance & Cloud
  • Design and optimize relational (PostgreSQL, MySQL) and non-relational databases for high-concurrency systems.
  • Implement distributed task execution and caching layers with Celery, Redis, or message brokers (Kafka/RabbitMQ).
  • Containerize services using Docker and collaborate on deployment workflows across cloud environments (AWS/GCP/Azure).
  • Monitor pipeline latency, token costs, evaluation metrics (e.g., Ragas, TruLens), and system reliability.

Required Skills & Qualifications

• Experience: 6–7+ years of hands-on experience in full-stack software development with a heavy focus on Python.
• Core Backend: Deep proficiency in Python and modern asynchronous frameworks (FastAPI, Django/DRF, or Flask).
• RAG & GenAI Experience: Demonstrated track record building, tuning, and deploying production RAG pipelines, semantic search engines, and prompt-chaining architectures.
• Frontend Skills: Strong experience with modern frontend stacks (React.js, TypeScript, Next.js, HTML5, CSS3/Tailwind).
• Databases: Hands-on expertise with vector databases (Pinecone, Qdrant, Weaviate, or pgvector) alongside relational databases (PostgreSQL).
• System Design & API Standards: Deep understanding of microservices, API security (OAuth2, JWT), rate-limiting, and distributed systems.
• Tooling & DevOps: Strong command of Git, Docker, CI/CD pipelines, and cloud services (AWS/GCP).
• Problem Solving: Proven ability to break down complex architectural challenges and mentor mid-level/junior engineers.

Good-to-Have (Bonus Points)

• Experience with agentic frameworks (CrewAI, LangGraph, AutoGen).
• Familiarity with fine-tuning open-source models (Hugging Face ecosystem) and deploying on local or cloud inference engines (vLLM, Ollama, Triton).
• Prior experience in early-to-growth stage AI startup environments.