AI/ML Engineer – Agentic AI

Experience: 6–8 Years

Job Type: Full-time

Location: Remote

Job Summary

We are looking for an experienced AI/ML Engineer – Agentic AI to design, develop, and deploy production-grade AI applications powered by Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and autonomous AI agents.

The ideal candidate will have strong expertise in Python, LLM application development, agentic AI frameworks, RAG, vector databases, cloud platforms, and MLOps/AgentOps. You will work on intelligent systems capable of reasoning, planning, decision-making, tool usage, and multi-step task execution.

Key Responsibilities

- Design, develop, and deploy autonomous AI agents and agentic AI applications.
- Build LLM-powered applications using OpenAI, Azure OpenAI, Anthropic, and similar models.
- Implement agent architectures such as ReAct, Plan-and-Execute, tool-calling, and multi-agent systems.
- Design and develop scalable RAG pipelines, knowledge bases, and AI memory systems.
- Integrate AI agents with APIs, enterprise applications, databases, and external tools.
- Develop planning, reasoning, reflection, and orchestration workflows for LLM-based systems.
- Build production-ready solutions with a strong focus on performance, scalability, reliability, security, and cost optimization.
- Implement asynchronous and concurrent Python applications for high-throughput AI workloads.
- Monitor and optimize LLM and agent performance, latency, token usage, and operational costs.
- Establish MLOps/AgentOps practices, including CI/CD, observability, evaluation, prompt management, and model/version tracking.
- Collaborate with engineering, product,



and business teams to translate requirements into scalable AI solutions.

Required Skills & Qualifications
- 6–8 years of experience in AI/ML, software engineering, or related fields.
- Strong expertise in Python, including async programming, concurrency, APIs, and backend development.
- Hands-on experience building LLM-based applications and Agentic AI systems.
- Strong understanding of LLM concepts, prompt engineering, function/tool calling, reasoning, planning, and orchestration.
- Experience with agentic architectures such as:
- ReAct
- Plan-and-Execute
- Multi-Agent Systems
- Tool-using Agents
- Workflow-based Agents
- Experience with one or more AI/agent frameworks:
- LangChain
- LangGraph
- Semantic Kernel
- CrewAI
- Robust experience designing RAG pipelines and working with vector databases/search platforms such as:
- FAISS
- Pinecone
- Azure AI Search
- Experience with OpenAI, Azure OpenAI, Anthropic, or equivalent LLM platforms.
- Experience with Docker and Kubernetes.
- Good understanding of cloud platforms, preferably Microsoft Azure, with exposure to AWS or GCP being an advantage.
- Experience with CI/CD, monitoring, logging, observability, and production deployment.
- Understanding of LLM evaluation, prompt/version tracking, guardrails, and AI system reliability.

Good to Have
- Experience building multi-agent collaboration systems.
- Experience developing GenAI copilots and enterprise AI products.
- Knowledge of AI safety, responsible AI, guardrails, and LLM security.
- Experience with RL-based optimization or reinforcement learning techniques.
- Experience with model evaluation, benchmarking, and automated LLM testing.
- Experience integrating AI systems with enterprise platforms and business workflows.

Work Location: In person

📌 AI/ML Engineer (Noida)
🏢 WebSenor
📍 Noida