•Design and develop LLM-powered agents and multi-agent workflows for complex decision-making and automation.
•Build agentic systems with reasoning, planning, tool calling, memory and context management .
•Integrate LLMs with internal APIs, databases, business systems and external tools.
•Develop evaluation, validation and feedback loops to continuously improve agent quality and reliability.
•Build human-in-the-loop workflows where required for validation and decision-making.
•Own technical implementation from POC to production , including performance, latency, cost, reliability and observability.
•Research and experiment with emerging LLMs, agent frameworks and AI techniques to improve system capabilities.
•Work under the guidance of the AI Product Lead while independently owning assigned technical modules and outcomes.
What we're looking for
•2–3 years of experience in GenAI, ML, NLP, Conversational AI or related fields.
•Strong hands-on experience with LLMs, prompt engineering, RAG and agentic workflows .
•Strong Python and software engineering fundamentals.
•Experience with frameworks such as LangGraph, LangChain, Google ADK, CrewAI, AutoGen or equivalent.
•Experience with API integration, databases and production-grade AI systems.
•Strong problem-solving skills and ability to work through ambiguous technical problems independently .
•Ability to rapidly prototype, evaluate and productionize AI solutions.
Good to have
•Experience with multi-agent systems, AI evaluation
•Experience with LLM observability and monitoring tools.
•Exposure to cloud platforms such as AWS and containerized deployments.
•BFSI / lending / collections domain experience.
