AI Engineer (LLM & Agent Systems)

Keka Technologies Private Limited; Hyderabad; On-site; INR 1,500,000 - 2,700,000; Full time

Job summary

Keka Technologies Private Limited in Hyderabad seeks a Python software engineer to design and maintain AI-powered applications. You will build AI solutions using LLMs, LangChain/LangGraph, and develop RAG pipelines with semantic search.

Responsibilities include integrating APIs, building scalable backends with FastAPI, and collaborating with teams to prototype, test, and deploy AI features. Strong Python and OOP skills are required, with a focus on reliability and clean documentation.

Qualifications

• 2–3 years of professional Python software development experience.
• Strong Python and object-oriented programming skills.
• Experience with LangChain, LangGraph, or similar LLM orchestration frameworks.
• Solid understanding of Retrieval-Augmented Generation, embeddings, and vector search.

Responsibilities

• Design, develop, and maintain AI-powered applications using Python.
• Build AI solutions using LLMs and orchestration frameworks.
• Develop and optimise Retrieval-Augmented Generation pipelines and semantic search.
• Integrate REST APIs and third-party services into production-ready apps.
• Build backend services with Python and FastAPI.
• Work with vector databases and document processing pipelines.
• Collaborate with cross-functional teams to prototype, test, and deploy features.
• Write clean, documented code and participate in code reviews and CI/CD.
• Continuously explore emerging AI tools and best practices.

Skills

Python

Object-oriented programming

LLM orchestration

RAG concepts

Embeddings

Vector search

APIs integration

Cloud platforms

AI tooling

Tools

LangChain

LangGraph

FastAPI

Job description

• Design, develop, and maintain AI-powered applications using Python.
• Build AI solutions using Large Language Models (LLMs), LangChain, LangGraph, or similar frameworks.
• Develop and optimise Retrieval-Augmented Generation (RAG) pipelines and semantic search applications.
• Integrate REST APIs, third-party services, and AI models into production-ready applications.
• Build scalable backend services using Python and modern API frameworks such as FastAPI.
• Work with vector databases, embeddings, and document processing pipelines.
• Collaborate with cross-functional teams to prototype, test, and deploy AI-driven features.
• Write clean, maintainable, and well-documented code following software engineering best practices.
• Participate in code reviews, testing, and CI/CD processes.
• Continuously explore and adopt emerging AI tools, frameworks, and best practices.

Required Skills & Qualifications

• 2–3 years of professional experience in Python software development.
• Strong proficiency in Python and object-orientated programming.
• Experience with LangChain, LangGraph, or similar LLM orchestration frameworks through professional or personal projects.
• Good understanding of Retrieval-Augmented Generation (RAG), prompt engineering, embeddings, and vector search concepts.
• Familiarity with vector databases such as Chroma, FAISS, Pinecone, or :.
• Comfortable integrating APIs, SDKs, and third-party services.
• Familiarity with cloud platforms such as AWS, Azure, or GCP.
• Daily experience using modern AI-assisted development tools such as Cursor or similar AI coding assistants.
• Strong problem-solving skills, curiosity, and a willingness to learn new technologies.

Nice to Have

• Personal projects, GitHub repositories, or open-source contributions involving LLMs or AI applications.
• Experience with Docker and basic CI/CD concepts.
• Exposure to React, Next.js, or TypeScript.
• Familiarity with AI evaluation, guardrails, or Model Context Protocol (MCP).
• Experience building AI copilots, chatbots, or workflow automation solutions.

What We're Looking For

We're looking for engineers who are passionate about building AI products and eager to learn. You don't need to be an expert in Kubernetes, multi-agent systems, or advanced cloud architecture from day one. If you have a strong Python foundation, have built interesting LLM-based projects, enjoy working with APIs, and are excited to grow in generative AI, we'd love to hear from you.