AI Engineer

Job Overview

We are building next-generation AI-powered products and are looking for a hands-on AI Engineer who thrives in fast-paced environments and loves solving real-world problems. This role involves designing, building, and scaling intelligent backend systems using Large Language Models (LLMs), agent frameworks, and modern backend technologies.

You will work closely with product, engineering, and AI teams to develop production-ready AI solutions that are efficient, scalable, and impactful.

Work-type:

Location:

Expereicne:

Key Responsibilities

• Design, develop, and scale AI-powered backend systems
• Build and maintain APIs using Django / FastAPI
• Implement and optimize LLM-based solutions, including:
• RAG pipelines
• Tool-calling agents
• Agentic AI Frameworks
• Work with frameworks such as LangChain, LangGraph, LangSmith, Agent Orchestration, and MCP/A2A protocols
• Build systems like:
• Web search, SQL agents, Data bots
• Supervised and structured AI workflows
• Image AI (DALLE / Stable Diffusion)
• Voice-based AI systems
• Integrate and manage Vector Databases (Pinecone, pgvector, Weaviate, Qdrant, etc.)
• Optimize systems for performance, reliability, and cost efficiency
• Containerize applications using Docker and manage code via GitHub
• Collaborate with cross-functional teams to deliver production-grade AI features

Must-Have Qualifications

• Strong proficiency in Python and backend development
• Hands-on experience with Django / FastAPI
• Solid understanding of LLMs, LangChain, LangGraph, and agent-based architectures
• Experience with tool calling and agent frameworks
• Working knowledge of Vector Databases
• Experience with APIs, Webhooks, and WebSockets
• Familiarity with Docker and version control (GitHub)
• Exposure to cloud platforms (AWS / GCP / Azure)

Nice-to-Have Skills

• Experience with AutoGen, CrewAI, or MCP
• Hands-on experience building production-grade RAG systems
• Understanding of microservices architecture
• Experience with monitoring, logging, and system observability
• Exposure to performance optimization and scalable AI deployments