Senior AI Engineer

Quess; Bengaluru; On-site; INR 3,000,000 - 6,000,000; Full time

Job summary

Quess in Bengaluru seeks an AI Engineer to design, implement, and optimize agent workflows using LangGraph, Python, and modern LLM ecosystems. You will build autonomous reasoning systems, integrate tools and APIs, and create scalable pipelines powering enterprise-grade AI applications.

The ideal candidate has 6+ years of software development, 3+ years Python, and hands-on AI/LLM engineering experience. You will work with LangGraph or LangChain, implement tool calling, memory management, and JSON

Qualifications

• 6+ years of software development experience.
• 3+ years Python development (OOP, async programming, API development).
• 1+ year hands-on AI/LLM engineering experience.
• Experience building AI agents using LangGraph or LangChain.
• Strong prompt engineering, tool calling, state/graph workflow design, and structured output generation.

Responsibilities

• Design and implement agentic workflows using LangGraph, LangChain, or similar orchestration frameworks.
• Develop LLM-powered agents with tool calling, state management, memory handling, and decision-based execution paths.
• Build and maintain Python-based services, tools, and utilities supporting agent workflows.
• Integrate external systems, APIs, vector databases, and enterprise data sources into agent pipelines.
• Design, implement, and optimize RAG pipelines, embeddings workflows, and contextual reasoning flows.
• Optimize agent performance, cost, and reliability; implement guardrails, validations, and structured output patterns.
• Troubleshoot and resolve issues related to agent logic, model behavior, integrations, and workflow execution.
• Document architecture, configurations, design decisions, and best practices for agent development.
• Collaborate with architects, AI engineers, and cross-functional teams to deliver end-to-end AI capabilities.

Skills

Python

AI/LLM

Tools

LangGraph

LangChain

Job description

Mandatory skills - Python, AI/LLM, LangGraph (preferred), LangChain

The AI Engineer will design, implement, and optimize AI agent workflows using LangGraph, Python, and modern LLM ecosystems. This role involves designing autonomous reasoning systems, integrating tools and APIs, and creating scalable pipelines that power enterprise-grade AI applications. The ideal candidate has strong software engineering fundamentals, practical AI engineering experience, and a passion for building robust, production-ready agent solutions.

Responsibilities:

• Design and implement agentic workflows using LangGraph, LangChain, or similar orchestration frameworks.
• Develop LLM-powered agents with capabilities such as tool calling, state management, memory handling, and decision-based execution paths.
• Build and maintain Python-based services, tools, and utilities supporting agent workflows.
• Integrate external systems, APIs, vector databases, and enterprise data sources into agent pipelines.
• Design, implement, and optimize RAG pipelines, embeddings workflows, and contextual reasoning flows.
• Optimize agent performance, cost, and reliability; implement guardrails, validations, and structured output patterns.
• Troubleshoot and resolve issues related to agent logic, model behavior, integrations, and workflow execution.
• Document architecture, configurations, design decisions, and best practices for agent development.
• Collaborate with architects, AI engineers, and cross-functional teams to deliver end-to-end AI capabilities.

Skill Set Required

• 6+ years of overall software development experience.
• 3+ years of Python development (OOP, async programming, API development; packaging, modularity, testing).
• 1+ year of hands-on AI/LLM engineering experience.
• Experience building AI agents using LangGraph (preferred), LangChain, or similar state-graph/agent frameworks.
• Strong understanding of prompt engineering, tool/function calling, state/graph workflow design, and structured output generation (JSON, Pydantic).
• Experience with vector databases (FAISS, Pinecone, Weaviate, Chroma, etc.).
• Proficiency integrating with OpenAI, Azure OpenAI, Anthropic, or other LLM providers.
• Familiarity with CI/CD workflows, Git, and cloud deployment environments (Azure/AWS/GCP).
• Strong debugging, problem-solving, and system design skills.