Agentic AI Developer

Accountabilities:: Design, develop, and optimize autonomous AI agents capable of reasoning, planning, reflection, decision-making, and multi-step task execution. Build multi-agent architectures and state-based workflows using frameworks such as LangGraph, AutoGen, CrewAI, or comparable custom orchestration platforms. Develop reliable agent loops that enable LLMs to select tools, execute actions, evaluate results, and adapt their approach when required. Integrate enterprise databases, internal applications, and external APIs with AI agents while implementing appropriate authentication, security boundaries, schema validation, and error handling. Design short-term and long-term memory mechanisms that allow agents to maintain relevant context throughout extended workflows and interactions. Develop automated evaluation frameworks to assess agent performance, reliability, task completion, reasoning quality, and failure scenarios. Monitor and optimize token consumption, latency, execution costs, and overall system performance. Implement safety mechanisms and guardrails to reduce hallucinations, constrain unintended actions, and prevent unsafe or uncontrolled agent behavior. Collaborate with engineering and AI teams to translate complex business requirements into scalable, production-ready agentic AI solutions. Requirements: 3–7 years of professional experience in software engineering, AI development, machine learning, or a closely related field, including hands-on experience with generative AI or agentic systems. Advanced proficiency in Python , including asynchronous programming and the development of scalable AI services. Strong practical knowledge of major LLM provider APIs, such as OpenAI, Anthropic, Mistral, or equivalent platforms. Hands-on experience developing agentic applications using LangChain, LangGraph, AutoGen, CrewAI , or similar agent orchestration frameworks. Good understanding of multi-agent architectures, tool calling, workflow orchestration, prompt design, context management, and LLM-based application development. Working knowledge of vector databases such as Pinecone, Qdrant, or Weaviate, as well as relational databases and data-access patterns. Experience with Docker and containerized application development. Strong understanding of software engineering fundamentals, including modular architecture, clean code, unit testing, version control, and production-quality development practices. Experience establishing rigorous testing and evaluation methodologies for AI systems, including handling edge cases and failure modes. Strong analytical, problem-solving, communication, and collaboration skills, with the ability to work effectively in a fast-moving AI engineering environment. Bachelor's degree in Computer Science, Engineering, Artificial Intelligence, Data Science, or a related technical discipline. Benefits: Annual compensation of approximately INR 2,500,000–4,000,000 CTC , depending on experience and skills. Full-time, mid-to-senior-level opportunity. Remote-friendly working model with flexibility across India. Location options including Bangalore, Pune, hybrid, or remote across India . Opportunity to work on advanced agentic AI, multi-agent systems, LLM applications, and intelligent automation. Exposure to modern AI frameworks, LLM platforms, vector databases, APIs, and cloud-ready engineering practices. Opportunity to contribute to production-grade AI systems designed to automate complex workflows and real-world business processes. Collaborative environment focused on experimentation, engineering excellence, and emerging generative AI technologies.