Python, Gen AI at VY SYSTEMS PRIVATE LIMITED · Hyderabad · 8 - 15 years · ₹5L - ₹25L / yr · Profitable · Posted 5 Oct 2026

Role Overview
We are looking for a skilled Python Full Stack / Agentic AI Engineer to design, develop, and deploy AI-powered applications and intelligent agentic workflows. The ideal candidate should have strong expertise in Python, FastAPI, LLMs, RAG, LangChain/LangGraph, and modern full-stack development.
You will work on building scalable backend services, integrating Large Language Models, developing AI agents, implementing Retrieval-Augmented Generation (RAG) pipelines, and creating production-ready AI applications.
Key Responsibilities
- Design and develop scalable backend applications using Python and FastAPI.
- Build and deploy Agentic AI solutions using LLMs and agent frameworks.
- Develop multi-step and multi-agent workflows using LangChain and LangGraph.
- Design and implement RAG (Retrieval-Augmented Generation) pipelines.
- Integrate LLMs such as OpenAI, Azure OpenAI, Anthropic, Gemini, or open-source models.
- Develop prompt engineering strategies and structured LLM workflows.
- Work with vector databases and embedding models for semantic search and knowledge retrieval.
- Build APIs and microservices for AI-powered applications.
- Integrate AI services with databases, third-party APIs, and enterprise systems.
- Develop conversation memory, tool calling, function calling, and agent orchestration capabilities.
- Implement evaluation, monitoring, logging, guardrails, and error handling for AI applications.
- Optimize applications for performance, scalability, reliability, and cost.
- Collaborate with product managers, frontend developers, data engineers, and other stakeholders.
- Write clean, maintainable, well-tested, and production-ready code.
- Participate in architecture discussions, code reviews, testing, and deployment activities.
Required Skills
Programming & Backend
- Strong proficiency in Python.
- Hands-on experience with FastAPI, REST APIs, and backend development.
- Strong understanding of asynchronous programming, API design, authentication, and middleware.
- Experience with SQL/NoSQL databases.
Generative AI / Agentic AI
- Strong understanding of LLMs and Generative AI.
- Hands-on experience building AI Agents / Agentic AI applications.
- Experience with LangChain and/or LangGraph.
- Knowledge of agent orchestration, tool calling, function calling, memory, and workflow management.
- Strong understanding of prompt engineering.
RAG
- Experience designing and implementing RAG architectures.
- Knowledge of document ingestion, chunking, embeddings, vector search, retrieval, reranking, and response generation.
- Experience with vector databases such as FAISS, Chroma, Pinecone, Weaviate, Qdrant, or similar.
LLM & AI Integration
- Experience integrating commercial or open-source LLMs.
- Understanding of embeddings, context windows, temperature, token usage, and model selection.
- Experience with structured outputs and LLM-based workflows.
- Familiarity with LLM evaluation and observability is a plus.
Full Stack
- Working knowledge of HTML, CSS, JavaScript/TypeScript.
- Experience with React.js or similar frontend frameworks is preferred.
- Ability to integrate frontend applications with Python/FastAPI services.

About VY SYSTEMS PRIVATE LIMITED
About
Vy Systems is a Global Technology consulting, Solutions, and Managed Technology Services company. We service our customers with ‘RESPONSIVENESS’ as a key factor and we believe that timely response to any transaction increases the operational efficiency and accelerates the revenue and profitability to our customers.
The Company is founded and managed by a team of professionals having more than two+ decades of global experience in the business of Technology Consulting and Services.
Tech stack
Similar jobs (10)
Role Overview
We are looking for a Python Developer with strong experience in Generative AI and LLM-based applications. The candidate should have hands-on experience building AI solutions using Python, RAG, LangChain/LangGraph, and related GenAI technologies.
Mandatory Skills
Python, GenAI/LLM, RAG, LangChain/LangGraph, Agentic AI, FastAPI, REST API, Vector Database, Prompt Engineering, Microservices
Key Responsibilities
- Develop and maintain applications using Python and modern frameworks.
- Build GenAI/LLM-based applications and solutions.
- Develop RAG pipelines using vector databases.
- Work with LangChain/LangGraph for LLM and agent-based applications.
- Develop and integrate REST APIs using FastAPI.
- Implement Agentic AI workflows and AI-powered features.
- Integrate LLMs with existing applications and microservices.
- Apply prompt engineering techniques to improve AI application performance.
Role: Python + Agentic AI Engineer
We are looking for an experienced Python + Agentic AI Engineer with strong expertise in developing AI-powered applications and autonomous agent-based solutions.
Key Skills / Requirements:
• Strong hands-on experience in Python
• Experience with Agentic AI / AI Agents
• Hands-on with LangChain / LangGraph or similar agent frameworks
• Experience with Generative AI and LLMs
• Strong understanding of RAG (Retrieval-Augmented Generation) and Vector Databases
• Experience developing REST APIs using FastAPI
• Knowledge of Multi-Agent Systems, Tool/Function Calling and Agent Workflows
• Experience integrating LLMs with enterprise applications/APIs
• Exposure to cloud-based AI services is an advantage
Preferred Profile: Python Developer / AI Engineer / Generative AI Engineer / Agentic AI Engineer with hands-on experience building production-ready AI solutions.
Job Description
We are looking for an experienced Python Full Stack – GenAI / Agentic AI Engineer with 7+ years of experience in software development and strong hands-on expertise in Python backend development, React JS, Generative AI, and Agentic AI.
The ideal candidate should have experience building scalable backend services, modern web applications, and AI-powered applications using LLMs, RAG, agentic frameworks, and cloud platforms.
Key Responsibilities
- Design, develop, and maintain scalable backend applications using Python.
- Develop robust REST APIs and microservices using FastAPI, Flask, or Django.
- Design API architecture, authentication mechanisms, error handling, and integrations.
- Develop responsive and interactive frontend applications using React JS.
- Work with React components, hooks, state management, and API integrations.
- Build and integrate Generative AI and Agentic AI applications using LLMs.
- Develop AI agents using frameworks such as LangChain and LangGraph.
- Implement RAG, embeddings, vector search, tool calling, memory, planning, and reasoning.
- Design and implement multi-agent systems and AI workflows.
- Apply prompt engineering techniques and appropriate guardrails for AI applications.
- Integrate AI applications with cloud-based AI platforms and services.
- Deploy applications using containers and cloud platforms.
- Work with CI/CD pipelines and application monitoring.
- Collaborate with cross-functional teams to design and deliver scalable solutions.
Required Skills
- 7+ years of overall software development experience.
- Strong hands-on experience in Python.
- Strong experience with FastAPI and REST API development.
- Experience with microservices architecture and API design.
- Hands-on experience with React JS.
- Strong experience in Generative AI / LLM applications.
- Hands-on experience in Agentic AI development.
- Experience with LangChain / LangGraph.
- Strong understanding of RAG, embeddings, vector search, and tool calling.
- Experience with multi-agent systems, memory, planning, and reasoning.
- Experience with at least one major cloud platform – AWS / Azure / GCP.
- Experience with containers, CI/CD, deployment, and monitoring.
Preferred Skills
- Google ADK
- Semantic Kernel
- Azure OpenAI
- Vertex AI
- AWS Bedrock
- Docker / Kubernetes
- AI application monitoring and observability
- Frontend testing and application performance optimization
Opportunity Details
Role: Python Full Stack – GenAI / Agentic AI Engineer
Experience: 7+ Years
Location: Hyderabad
Employment: Permanent Position
Work Mode: As per client requirement
Mandate Skills: Python, FastAPI, React JS, Agentic AI, LangChain/LangGraph, RAG, LLM, Cloud
Interview Focus Areas
Candidates should be prepared to demonstrate practical experience in:
- Python backend development
- FastAPI and REST APIs
- Microservices and API design
- React JS
- LLM / Generative AI applications
- Agentic AI architecture
- LangChain / LangGraph
- RAG and vector search
- Tool calling and multi-agent systems
- Cloud deployment and CI/CD
Python (Gen AI or Agentic AI) - Hyderabad
7 + years of exp with more than 2 + years on Gen AI/Agentic AI.
Design and implement Generative AI and Agentic AI capabilities using LLM platforms and frameworks such as LangChain, LangGraph, Google ADK, Semantic Kernel, or equivalent.
Implement tool calling, RAG, memory, planning, reasoning, multi-agent orchestration, structured outputs, and human approval controls.
Integrate applications with REST APIs, relational and NoSQL databases, vector stores, message queues, and enterprise systems.
We are currently hiring for the position of Python – GenAI / Agentic AI Engineer for one of our esteemed clients.
Please find the opportunity details below:
Position: Python – GenAI / Agentic AI Engineer
Location: Hyderabad
Experience: 7+ Years
GenAI / Agentic AI Experience: 2+ Years
Work Mode: Hybrid
Job Description
We are looking for an experienced Python professional with strong hands-on expertise in Generative AI / Agentic AI and LLM-based application development.
Core Mandatory Skills
- Python
- Generative AI / GenAI
- Agentic AI
- LLM
- LangChain / LangGraph
- Google ADK / Semantic Kernel / Equivalent Agent Frameworks
- RAG
- Tool Calling
- Memory, Planning & Reasoning
- Multi-Agent Orchestration
- Structured Outputs
- Human-in-the-Loop / Human Approval Controls
- REST APIs
- Relational & NoSQL Databases
- Vector Stores / Vector Databases
- Message Queues
- Enterprise System Integration
Key Responsibilities
- Design and implement Generative AI and Agentic AI capabilities using LLM platforms and frameworks.
- Build AI agents using LangChain, LangGraph, Google ADK, Semantic Kernel, or equivalent frameworks.
- Implement tool calling, RAG, memory, planning, reasoning, and multi-agent orchestration.
- Develop structured AI workflows with human approval controls.
- Integrate AI applications with REST APIs, databases, vector stores, message queues, and enterprise systems.
- Develop scalable and production-ready Python-based AI applications.
We are currently hiring for the position of Python – GenAI / Agentic AI Engineer for one of our esteemed clients.
Please find the opportunity details below:
Position: Python – GenAI / Agentic AI Engineer
Location: Hyderabad
Experience: 7+ Years
GenAI / Agentic AI Experience: 2+ Years
Work Mode: Hybrid
Job Description
We are looking for an experienced Python professional with strong hands-on expertise in Generative AI / Agentic AI and LLM-based application development.
Core Mandatory Skills
- Python
- Generative AI / GenAI
- Agentic AI
- LLM
- LangChain / LangGraph
- Google ADK / Semantic Kernel / Equivalent Agent Frameworks
- RAG
- Tool Calling
- Memory, Planning & Reasoning
- Multi-Agent Orchestration
- Structured Outputs
- Human-in-the-Loop / Human Approval Controls
- REST APIs
- Relational & NoSQL Databases
- Vector Stores / Vector Databases
- Message Queues
- Enterprise System Integration
Key Responsibilities
- Design and implement Generative AI and Agentic AI capabilities using LLM platforms and frameworks.
- Build AI agents using LangChain, LangGraph, Google ADK, Semantic Kernel, or equivalent frameworks.
- Implement tool calling, RAG, memory, planning, reasoning, and multi-agent orchestration.
- Develop structured AI workflows with human approval controls.
- Integrate AI applications with REST APIs, databases, vector stores, message queues, and enterprise systems.
- Develop scalable and production-ready Python-based AI applications.
Python Full Stack GenAI Engineer
Experience: 5+ Years
Location: Bangalore / Hyderabad
Role Overview:
We are looking for a Python Full Stack GenAI Engineer with strong hands-on experience in Python development and Generative AI solutions.
Must-Have Skills:
- Python – Strong hands-on experience
- Generative AI / GenAI
- LLMs & Prompt Engineering
- LangChain / LangGraph
- RAG & Vector Databases
- REST APIs / FastAPI
- React.js / Frontend development
- SQL
- AI Agent / Agentic AI experience is a plus
Responsibilities:
- Develop scalable Python-based applications with GenAI capabilities
- Build LLM, RAG and AI Agent solutions
- Develop REST APIs using FastAPI
- Integrate AI services with full-stack applications
- Work with frontend technologies such as React.js
- Design and optimize production-ready GenAI solutions
Interested candidates can apply with their updated resume.
🚀 Hiring: Python GenAI / Agentic AI Engineer
📍 Location: Hyderabad
💼 Experience: 7+ Years
🤖 GenAI / Agentic AI: 2+ Years
Mandatory Skills:
• Strong Python development experience
• Generative AI / Agentic AI
• LLMs & Prompt Engineering
• LangChain / LangGraph
• RAG & Vector Databases
• AI Agents / Multi-Agent Systems
• FastAPI / REST APIs
• LLM Integration
• Microservices & API Architecture
• Git & CI/CD
Looking for candidates with strong hands-on experience in building GenAI/Agentic AI solutions using Python, LLMs, RAG, and AI Agent frameworks.
The recruiter has not been active on this job recently. You may apply but please expect a delayed response.
Location: Pune / Gurgaon
Position: AI Engineer
work mode: WFO
Job Description.
Job responsibilities:
- Responsibility for design, implementation and deployment of Generative AI, Agentic frameworks at scale
- Strong in programming - Python a
- Previous experience of working on Computer Vision projects and VLM /VLAM models.
- In depth awareness of Transformer architectures and End to End Deep neural networks
- Full stack AI / ML development experience
- Design, build & maintain efficient and reliable Agentic / Generative AI code leveraging pipelines
- Hosting and deployment knowledge in GCP or AWS or Azure along with advanced engineering concepts to build user friendly UI interface for easy adoption.
Requirements:
· 4 to 8 years overall years of experience (Agentic AI, Generative AI, VLM, VLAM and LLM) with significant exposure in Development, Architecture design, scaling and hosting in cloud.
Must Have –
· Architecting and solutioning experience with Python and FAST API, Agentic Ai frameworks, VLMs, VLAMs, Open source LLM’s and Code based LLM models at scale with - Langchain / Ollama, embeddings, Memory Management etc.,
· Practical experience in implementing Explainable and ethical AI models Practical experience in implementing frameworks like RAG/ CAG/ Self-reflective RAG etc.,
· Experience in cloud hosting either AWS or Azure or GCP.
· Experience in ML-OPS - Implement a feedback mechanism to continually improve the model over time through feedback loop and monitoring KPI’s in production.
· Experience with Quantization and Kubernetes or docker
Good to have
· gRPC implementation to expose the API’s on a server for easy usage and good user interface
· Streamlit front end creation
· Experience with SAFe framework deliveries.
Support with design and build to prove out agentic AI solution flow by working with other data
scientists and engineers to build, train Large Language Model (LLM) architectures, RAG
systems, and autonomous agentic workflows
Key qualifications:
>> AI solution design & Development: Design Agentic AI solutions using RAG (Retrieval-
Augmented Generation) and orchestration frameworks like LangGraph or LangChain.
>> Model Fine-Tuning: Solid understanding and experience with Pre-train, fine-tune, and
optimize open-source like BERT, LLama, and other proprietary foundation models for domain-
specific tasks
>> Solid Stats and ML foundations and (vibe) coding skills with Python, PySpark
>> Implement validation frameworks and tracing practices (using tools like Arize) to monitor
agent behavior, guard against model drift, and ensure compliance
>> Collaborate with Engineering to deploy models securely on cloud and on-prem ecosystems






