Acceldata is reimagining the way companies observe their Data!
Acceldata is the pioneer and leader in data observability, revolutionizing how enterprises manage and observe data by offering comprehensive insights into various key aspects of data, data pipelines and data infrastructure across various environments. Our platform empowers data teams to manage products effectively by ensuring data quality, preventing failures, and controlling costs.
Senior AI Engineer – Backend Engineering (Agentic AI) About the Role We are looking for an AI Engineer with strong backend engineering experience and hands-on experience building Agentic AI systems. The ideal candidate should have built and deployed AI agents capable of reasoning, planning, using tools, interacting with multiple systems, and executing multi-step workflows in real-world applications. What You’ll Do Design, develop, and maintain scalable backend services and APIs. Build and deploy Agentic AI systems that can reason, plan, use tools, and execute complex workflows. Develop multi-agent systems and orchestrate interactions between multiple AI agents. Build LLM-powered applications using RAG, vector databases, embeddings, and semantic search. Integrate LLMs and AI models into production-grade backend applications. Develop reliable agent workflows with appropriate memory, context management, and guardrails. Optimize AI application performance, scalability, reliability, and response times. Collaborate with product and engineering teams to take AI capabilities from concept to production. What We’re Looking For Strong programming experience in Python, Java, or Go. Good understanding of backend development, REST APIs, microservices, and distributed systems. Proven hands-on experience building and deploying Agentic AI systems in production. Experience with agent frameworks such as LangGraph, LangChain, CrewAI, AutoGen, or similar. Strong understanding of LLMs, prompt engineering, tool/function calling, and orchestration. Experience building RAG-based applications using vector databases and embeddings. Understanding of agent memory, planning, reasoning, evaluation, and guardrails. Good understanding of databases (SQL/NoSQL), data structures, algorithms, and system design. Strong debugging, problem-solving, and analytical skills. Good to Have Experience with Kafka, Spark, or other distributed data technologies. Familiarity with cloud platforms, Docker, Kubernetes, and CI/CD. Experience with LLM observability, evaluation, and performance optimization.