Area(s) of responsibility

We are hiring hands-on Developers and Engineers to design, build, and deploy production-grade Agentic AI solutions on Aisera and similar platforms (ServiceNow AI and open agent frameworks) across client engagements. You will develop autonomous and multi-agent systems that reason, plan, and execute — integrating LLMs with enterprise systems to automate ITSM, operations, and business workflows, and remaining hands-on through to delivery.

Key Responsibilities

• Develop, configure, and deploy AI agents using Aisera’s platform and comparable agentic AI toolsets to solve real-world client workflows.
• Build autonomous and multi-agent systems capable of planning, reasoning, tool selection, and task execution.
• Design and implement RAG pipelines, function/tool calling, memory and context management, and agent orchestration.
• Integrate agents with external systems — APIs, webhooks, databases, CRMs, ITSM platforms, and data pipelines — for seamless workflow execution.
• Apply prompt engineering and configuration tuning to optimize agent accuracy, latency, and cost in complex enterprise environments.
• Translate business requirements into functional and technical agent designs; run interactive demos and PoCs and iterate on feedback.
• Build scalable backend services/microservices for AI applications; ensure testing, monitoring, and CI/CD best practices.
• Implement AI governance, security, and compliance controls (auth flows, responsible-AI safeguards, observability of agent behavior).
• Troubleshoot, monitor, and continuously improve deployed agents using data-driven evaluation (A/B testing, performance monitoring).

Required Skills & Experience

• 8–12 years in software development, AI/ML engineering, or systems integration, with recent hands-on Agentic AI / LLM delivery.
• Hands-on experience with Aisera or comparable agentic AI / conversational AIOps platforms (ServiceNow AI Agents, Automation Anywhere, similar).
• Strong programming in Python (primary), plus Java and/or JavaScript; clean, efficient, production-quality code.
• Proven experience building agents with LLM frameworks — LangChain, LangGraph, CrewAI, AutoGen, or PydanticAI.
• Solid understanding of LLMs, embeddings, vector databases, RAG, function calling, and agent evaluation.
• Experience with Model Context Protocol (MCP) and multi-agent architectures (preferred).
• Integration experience: REST APIs, webhooks, data pipelines; OAuth/OIDC/JWT authorization flows.
• Cloud & DevOps: AWS, Azure, or GCP, containerization (Docker/Kubernetes), CI/CD, and monitoring.
• Familiarity with AI/LLM observability tooling (Langfuse, ELK) is highly desirable.
• Strong problem-solving, customer-facing communication, and the ability to work independently.

Qualifications

• Bachelor’s or Master’s in Computer Science, AI, Data Science, or a related field.
• Relevant cloud/AI certifications are a plus.
• Knowledge of AI governance frameworks (e.g., ISO/IEC 42001) is a nice-to-have.