AI Workflow Engineer

Job Description

Role Overview:

We are looking for an AI Workflow Engineer to design, develop, and deploy intelligent workflows powered by Generative AI, Large Language Models (LLMs), AI agents, APIs, and automation platforms.

The role involves converting business and engineering problems into reliable AI-powered workflows that can automate repetitive tasks, process unstructured information, make decisions, call external tools, and produce structured outputs.

The ideal candidate is strong in Python, APIs, LLM applications, workflow automation, prompt engineering, RAG, and agent orchestration.

Key Responsibilities:

1. AI Workflow Development
Design and develop end-to-end AI workflows.
Build multi-step LLM pipelines and agentic workflows.
Connect LLMs with APIs, databases, business applications, and external tools.
Convert manual business processes into automated AI workflows.
Build reusable AI components, agents, prompts, and workflow templates.

2. LLM & Generative AI
Integrate models such as OpenAI, Claude, Gemini, or open-source LLMs.
Develop structured prompts and prompt templates.
Implement function/tool calling and structured JSON outputs.
Optimize workflows for accuracy, latency, reliability, and token/cost efficiency.
Implement fallback mechanisms when an AI model produces an invalid or unreliable response.

3. AI Agents & Orchestration
Build AI agents capable of planning and executing multi-step tasks.
Implement tool calling and function routing.
Design multi-agent workflows where multiple specialized agents collaborate.
Work with frameworks such as LangChain, LangGraph, CrewAI, AutoGen, or similar technologies.
Explore and implement MCP (Model Context Protocol) integrations where appropriate.

4. RAG & Knowledge Systems
Build Retrieval-Augmented Generation (RAG) pipelines.
Process documents such as PDFs, Word files, Excel files, websites, and reports.
Implement document ingestion, chunking, embeddings, retrieval, and generation.
Work with vector databases such as Pinecone, Weaviate, Qdrant, Chroma, or similar systems.
Improve retrieval quality and reduce hallucinations.

5. API & System Integration
Integrate AI workflows with REST APIs and third-party services.
Build backend services using Python/FastAPI or similar frameworks.
Connect workflows to databases, cloud storage, CRMs, email systems, and enterprise applications.
Implement authentication, error handling, retries, rate limiting, and logging.

6. Workflow Automation
Build automation using platforms such as:n8n
Zapier
Microsoft Power Automate
Apache Airflow
Temporal
AWS Step Functions
Schedule and orchestrate automated processes.
Create event-driven workflows where appropriate.
Monitor workflow execution and handle failures.

7. Data Processing
Extract and transform structured and unstructured data.
Build ETL/data-processing pipelines.
Process PDFs, CSVs, Excel files, databases, web data, and business documents.
Convert unstructured information into structured tables, reports, summaries, or alerts.

Required Technical Skills:

Programming
Strong Python programming skills.
Understanding of asynchronous programming is a plus.
Knowledge of REST APIs and backend development.
SQL and database fundamentals.
Generative AI
LLM APIs
Prompt engineering
Structured outputs
Function/tool calling
Context management
AI agents
Agent orchestration
RAG
Frameworks
Experience with one or more:

LangChain
LangGraph
CrewAI
AutoGen
LlamaIndex
Semantic Kernel
Automation
Experience with one or more:

n8n
Zapier
Power Automate
Airflow
Temporal
AWS Step Functions
Databases
PostgreSQL / MySQL
MongoDB
Redis
Vector databases such as Pinecone, Qdrant, Weaviate, or Chroma
Cloud & Deployment
AWS / Azure / Google Cloud
Docker
Kubernetes — good to have
CI/CD
Git/GitHub

Preferred Qualifications
Bachelor’s degree in Computer Science, Information Technology, Engineering, AI, Data Science, or a related field.
2–5 years of experience in software engineering, automation engineering, AI engineering, data engineering, or backend development.
Experience building at least one production-quality AI application, agent, workflow, or automation system.
Experience working with LLM APIs beyond simply using ChatGPT through a web interface.
Knowledge of AI security, prompt injection, data privacy, and responsible AI is a plus.
Experience with enterprise systems and third-party API integrations is beneficial.

Key Performance Indicators :

Reduction in manual work
Hours saved through automation
AI workflow accuracy
Workflow completion rate
Reduction in AI/API costs
System response time
Number of workflows successfully deployed
User/team adoption
Reduction in operational errors
Production reliability