AgenticAI Workflow Engineer | Onsite

Agentic AI Workflow Engineer

We are seeking an Agentic AI Workflow Engineer to design, build, and optimize intelligent AI-driven workflows using Large Language Models (LLMs), AI agents, and enterprise automation frameworks. You will develop agentic applications that can reason, retrieve knowledge, interact with enterprise systems, and automate complex business processes.

The ideal candidate combines strong software engineering fundamentals with hands-on experience in Generative AI application development, agent orchestration, RAG pipelines, prompt engineering, and API integrations.

Technical Stack:

LLMs:

OpenAI GPT, Claude, Gemini, Llama, Mistral, and other open-source LLMs.

Agent Frameworks:

LangGraph, LangChain, LlamaIndex, Semantic Kernel, CrewAI, AutoGen.

Agentic AI Concepts:

Multi-Agent Systems (MAS), Agent Planning, Tool Calling, Memory Management, Human-in-the-Loop (HITL) workflows.

Development:

Python, FastAPI, REST APIs, Async Programming.

RAG & Knowledge Engineering:

Vector Databases, PostgreSQL, pgvector, Redis Vector Search, Elasticsearch, Embeddings, Semantic Search, Retrieval Optimization.

Workflow Orchestration:

LangGraph workflows, Agent State Management, Workflow Automation, Event-driven workflows.

Cloud & Deployment:

AWS/Azure/GCP, Docker, CI/CD pipelines, API deployment.

Tools:

Prompt Engineering, AI Workflow Design, LLM Evaluation, Agent Monitoring, GenAI Optimization.

Key Responsibilities:

• Develop and orchestrate AI agent workflows using LangGraph, LangChain, and multi-agent architectures.

• Design agent behaviors including:

• Goals and instructions

• Tool usage

• Reasoning flows

• Memory management

• Error handling and recovery

• Build RAG-based AI applications by integrating enterprise knowledge sources, vector databases, and embedding models.

• Develop AI agents capable of interacting with enterprise systems through APIs, databases, and external tools.

• Implement function calling and tool integrations enabling agents to perform real-world actions.

• Create reusable agent components, workflow templates, and AI automation patterns.

• Develop backend services and APIs using Python, FastAPI, and asynchronous programming.

• Optimize prompts, agent workflows, and retrieval strategies to improve:

• Accuracy

• Response quality

• Latency

• Cost efficiency

• Implement Human-in-the-Loop workflows for approval-based enterprise processes.

• Build evaluation pipelines to measure agent performance, hallucination rates, and task completion accuracy.

• Deploy and monitor GenAI applications using cloud platforms, containerization, and observability tools.

• Collaborate with AI architects, product managers, and domain teams to convert business processes into agentic AI solutions.

Required Qualifications:

• 3-6 years of experience in software engineering, AI engineering, or Generative AI application development.

• Hands-on experience building LLM-powered applications using Python.

• Strong understanding of:

• LLM concepts

• Prompt engineering

• RAG architecture

• AI agent workflows

• Vector search concepts

• Experience with agent frameworks such as:

• LangGraph

• LangChain

• LlamaIndex

• Semantic Kernel

• CrewAI

• Experience integrating LLM applications with REST APIs, databases, and enterprise systems.

• Knowledge of vector databases, embeddings, semantic search, and retrieval optimization techniques.

• Experience developing production-quality Python applications using FastAPI or similar frameworks.

• Familiarity with Docker, cloud deployment, CI/CD practices, and API security.

• Understanding of AI evaluation techniques including:

• Response quality assessment

• Prompt testing

• Agent workflow validation

• Exposure to AI governance concepts:

• Responsible AI

• Guardrails

• Data privacy

• Prompt injection prevention

Preferred Qualifications:

• Experience building autonomous AI agents or multi-agent workflows.

• Experience with enterprise automation, IT operations, customer service, or business process automation use cases.

• Experience with observability platforms for monitoring AI applications.

• Contributions to open-source AI frameworks or GenAI projects.