Join us as a hands-on Developer or Engineer focused on Agentic AI, leveraging platforms like Aisera and advanced AI frameworks. This role involves designing, building, and deploying sophisticated autonomous and multi-agent systems that integrate Large Language Models (LLMs) with enterprise solutions.

Your work will drive the automation of ITSM, operations, and critical business workflows. You'll be involved in the full lifecycle, from initial concept and development through to successful production delivery, ensuring seamless integration and efficient execution.

Develop, configure, and deploy advanced AI agents using Aisera and similar agentic AI toolsets to address complex client workflows. You will architect and implement autonomous, multi-agent systems featuring planning, reasoning, and dynamic tool selection.

Key tasks include designing RAG pipelines, managing memory and context, and orchestrating agent interactions. Integration with external systems such as APIs, webhooks, databases, and ITSM platforms is essential for enabling fluid workflow automation.

Optimize agent performance through prompt engineering and configuration tuning for accuracy, latency, and cost-efficiency. Translate business needs into technical agent designs, conduct demos, and iterate based on feedback. Build robust backend services and microservices, adhering to best practices in testing, monitoring, and CI/CD.

Implement essential AI governance, security, and compliance measures, including authentication, responsible AI safeguards, and behavior observability. Continuously monitor, troubleshoot, and enhance deployed agents using data-driven evaluation techniques like A/B testing.

We are seeking experienced professionals with 8-12 years in software development, AI/ML engineering, or systems integration, emphasizing recent, practical experience with Agentic AI and LLM delivery. A strong track record of building AI agents using frameworks such as LangChain, LangGraph, CrewAI, AutoGen, or PydanticAI is crucial.

Candidates must possess a deep understanding of LLMs, embeddings, vector databases, RAG, function calling, and agent evaluation methodologies. Proficiency in Python is primary, complemented by experience in Java and/or JavaScript, producing clean, production-ready code.

Experience with integrating agents via REST APIs, webhooks, and data pipelines, along with knowledge of OAuth/OIDC/JWT authorization flows, is required. Familiarity with cloud environments (AWS, Azure, GCP), containerization (Docker/Kubernetes), CI/CD, and monitoring tools is essential. Experience with AI/LLM observability tools is a significant advantage.

This role demands strong problem-solving capabilities, excellent customer-facing communication skills, and the ability to work autonomously.