Source description
About the role
About the Opportunity A fast-scaling AI-first tech firm in the Enterprise Automation Agentic AI space, we build autonomous, multi-agent systems that automate enterprise workflows, enhance decision intelligence, and power intelligent automation across banking, healthcare, and logistics. Our engineers ship scalable, LLM-powered agent architectures that operate across structured and unstructured data domains leveraging Python, LangChain, LlamaIndex, and open-source ML ecosystems to deliver real business impact. Role Responsibilities Design and deploy end-to-end agentic AI workflows orchestrating multiple LLM agents across tools, APIs, and data sources to automate complex business decisions. Build and optimize agent memory, planning, and tool-calling systems using LangGraph, AutoGen, or similar frameworks for context-aware, persistent interactions. Integrate LLMs (e.g., GPT-4, Llama 3, Mistral) with RAG pipelines, vector stores (FAISS, Pinecone), and function-calling modules to deliver high-accuracy, low-latency responses. Develop scalable AI agent backends in Python, containerized via Docker and orchestrated on Kubernetes (EKS/AKS), with observability via Prometheus/Grafana. Partner with product and data science teams to define agent personas, success metrics, and fallback/recovery logic for high-availability systems. Maintain engineering excellence: write clean, testable code, implement CI/CD pipelines, and document system architecture for team scalability. Skills Qualifications Must-Have Python LangChain LangGraph AutoGen RAG FAISS LLM Fine-Tuning Kubernetes Preferred LLM Agent Evaluation Frameworks (e.g., LangSmith, TruLens) Multi-Agent System Design Patterns Cloud Certification (AWS/Azure/GCP) Benefits Culture Highlights Work onsite in Hyderabad with a high-impact, research-driven team building next-gen agentic AI solutions. Access to latest LLM APIs, compute resources, and internal hackathons to prototype cutting-edge agent architectures. Flexible PTO, performance bonuses, and a mission-driven culture focused on shipping real AI products not just experiments. Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying. About the Opportunity A fast-scaling AI-first tech firm in the Enterprise Automation Agentic AI space, we build autonomous, multi-agent systems that automate enterprise workflows, enhance decision intelligence, and power intelligent automation across banking, healthcare, and logistics. Our engineers ship scalable, LLM-powered agent architectures that operate across structured and unstructured data domains leveraging Python, LangChain, LlamaIndex, and open-source ML ecosystems to deliver real business impact. Role Responsibilities Design and deploy end-to-end agentic AI workflows orchestrating multiple LLM agents across tools, APIs, and data sources to automate complex business decisions. Build and optimize agent memory, planning, and tool-calling systems using LangGraph, AutoGen, or similar frameworks for context-aware, persistent interactions. Integrate LLMs (e.g., GPT-4, Llama 3, Mistral) with RAG pipelines, vector stores (FAISS, Pinecone), and function-calling modules to deliver high-accuracy, low-latency responses. Develop scalable AI agent backends in Python, containerized via Docker and orchestrated on Kubernetes (EKS/AKS), with observability via Prometheus/Grafana. Partner with product and data science teams to define agent personas, success metrics, and fallback/recovery logic for high-availability systems. Maintain engineering excellence: write clean, testable code, implement CI/CD pipelines, and document system architecture for team scalability. Skills Qualifications Must-Have Python LangChain LangGraph AutoGen RAG FAISS LLM Fine-Tuning Kubernetes Preferred LLM Agent Evaluation Frameworks (e.g., LangSmith, TruLens) Multi-Agent System Design Patterns Cloud Certification (AWS/Azure/GCP) Benefits Culture Highlights Work onsite in Hyderabad with a high-impact, research-driven team building next-gen agentic AI solutions. Access to latest LLM APIs, compute resources, and internal hackathons to prototype cutting-edge agent architectures. Flexible PTO, performance bonuses, and a mission-driven culture focused on shipping real AI products not just experiments. Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.
More at Orbion Infotech