Agentic AI Engineer

Job Title: Agentic AI Engineer

Experience: 68 Years
Relevant GenAI/LLM Experience: Minimum 1–2 Years
Employment Type: Full-Time
Work Mode: As per business requirement
Location: As per business requirement

Job Summary

We are looking for an experienced Agentic AI Engineer with strong Python development and backend engineering expertise to design, develop, and deploy production-ready AI agent solutions.

The ideal candidate should have hands-on experience building LLM-powered applications, multi-agent systems, and stateful AI workflows using LangChain and LangGraph. The candidate should possess strong expertise in RAG pipelines, LLM integrations, API development, agent orchestration, and scalable cloud deployments.

We are looking for an engineering professional who can take AI solutions from proof of concept to production, with a strong focus on reliability, security, performance, observability, and scalability.

Key Responsibilities

• Design, develop, and deploy single-agent and multi-agent AI applications using LangChain and LangGraph.
• Build stateful agent workflows involving planning, routing, tool calling, memory management, delegation, and human-in-the-loop approvals.
• Develop and optimize Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking, embeddings, retrieval, reranking, and response generation.
• Integrate LLMs with enterprise APIs, databases, vector stores, search engines, and third-party services.
• Develop scalable backend services and REST APIs using Python, FastAPI, Flask, or similar frameworks.
• Implement reliable agent execution mechanisms, including structured outputs, error handling, retries, fallbacks, and workflow recovery.
• Build agent evaluation frameworks to measure accuracy, groundedness, task completion, latency, and cost.
• Implement observability, monitoring, and tracing for agent execution, LLM interactions, and tool calls.
• Apply AI security best practices, including access controls, prompt-injection mitigation, secrets management, data protection, and output validation.
• Optimize LLM performance, model selection, token consumption, infrastructure utilization, and operational costs.
• Develop unit, integration, regression, and end-to-end tests for AI workflows.
• Collaborate with cross-functional teams to translate business requirements into scalable AI solutions.
• Contribute to architecture design, technical documentation, code reviews, and engineering best practices.

Required Skills & Qualifications

• 6–8 years of overall experience in software engineering, backend development, data science, or related technical fields.
• Minimum 1–2 years of hands-on experience in Generative AI, LLM application development, or Agentic AI.
• Strong practical experience with LangChain and LangGraph.
• Proven experience designing and implementing multi-agent systems and complex agentic workflows.
• Strong proficiency in Python, object-oriented programming, data structures, design patterns, and clean-code principles.
• Hands-on experience developing production-grade backend applications using FastAPI, Flask, or similar frameworks.
• Strong understanding of LLM concepts, including prompt engineering, context management, embeddings, structured outputs, function calling, and tool integration.
• Hands-on experience implementing RAG solutions and integrating vector databases.
• Experience integrating LLM applications with enterprise systems, APIs, databases, and external tools.
• Understanding of agent evaluation, observability, tracing, monitoring, and AI guardrails.
• Experience with cloud platforms, preferably Microsoft Azure, Azure OpenAI, and Azure AI Foundry.
• Working knowledge of Docker, Git, CI/CD, and production deployment practices.
• Strong analytical, debugging, problem-solving, and communication skills.

Good-to-Have Skills

• Experience with machine learning and deep learning frameworks such as PyTorch and Scikit-learn.
• Knowledge of pandas, NumPy, and ML workflows.
• Experience with fine-tuning techniques such as LoRA and QLoRA.
• Experience with vector databases such as Azure AI Search, Pinecone, Weaviate, Milvus, Chroma, or FAISS.
• Familiarity with LangSmith, MLflow, OpenTelemetry, or similar LLM observability and evaluation platforms.
• Knowledge of Model Context Protocol (MCP) and standardized tool integration.
• Experience with event-driven architecture, message queues, and distributed systems.
• Knowledge of SQL, NoSQL databases, and data engineering pipelines.
• Experience with Kubernetes, model serving, prompt caching, semantic caching, and inference optimization.

Technology Stack

CategoryTechnologiesProgrammingPython, SQLAgentic AILangChain, LangGraphGenAI / LLMAzure OpenAI, Azure AI Foundry, LLM APIs, Function CallingRAG & Vector SearchAzure AI Search, Pinecone, Weaviate, FAISS, ChromaBackendFastAPI, Flask, REST APIs, PydanticCloud & DevOpsMicrosoft Azure, Docker, Kubernetes, Git, CI/CDObservabilityLangSmith, OpenTelemetry, MLflowMachine LearningPyTorch, Scikit-learn, pandas, NumPy

Ideal Candidate Profile

We are looking for candidates who:

• Have built and deployed real-world Agentic AI or LLM-powered applications.
• Have strong hands-on expertise in both LangChain and LangGraph.
• Can independently design and implement multi-agent architectures.
• Understand the complete AI application