AI Automation Engineer

Applicantz; Bengaluru; On-site; INR 1,500,000 - 2,600,000; Full time

Job summary

Applicantz is seeking an AI Automation Engineer to design, build, and operate AI-powered automations across business and engineering workflows. The role emphasizes hands-on development using LLMs, agentic frameworks, APIs, and workflow orchestration to convert complex processes into reliable production-grade automations.

You will implement MCP servers, develop end-to-end automation pipelines, and ensure secure, scalable solutions with performance monitoring and cost optimization.

Qualifications

• 3–5 years of professional experience in Software Engineering, Data Engineering, or Automation Engineering, including at least 1 year of hands-on LLM/AI experience.
• Strong Python development skills with API integration, asynchronous programming, testing, packaging, and maintainable code.
• Hands-on experience with LLM APIs such as OpenAI, Anthropic Claude, Gemini, or Amazon Bedrock in production settings.
• Hands-on experience with at least one agentic AI/orchestration framework (LangChain, LangGraph, LlamaIndex, CrewAI, Semantic Kernel, AutoGen).
• Experience building RAG systems using vector stores like pgvector, Pinecone, Weaviate, Qdrant, Milvus, or OpenSearch.
• Strong understanding of prompt engineering, context design, structured outputs, JSON schemas, tool/function calling, and validation.
• Familiarity with MCPs and exposing internal systems as agent tools via MCP servers.
• Strong experience with REST/GraphQL APIs, OAuth, token-based auth, webhooks, pagination, and rate limits.
• Working knowledge of SQL and data modeling.
• Experience with Git, code reviews, and CI/CD.
• Cloud experience with AWS, Azure, or GCP including compute, serverless, queues, secrets, and managed AI services.
• Basic Docker/containerization knowledge.
• Strong stakeholder-management skills, including requirements gathering, prototyping, demonstrations, and expectation management.

Responsibilities

• Build and deploy end-to-end AI automations and agentic workflows integrating LLMs with internal systems, APIs, and data sources.
• Design and implement RAG pipelines including chunking, embeddings, vector search, re-ranking, and grounded response generation.
• Develop tool/function-calling integrations to enable AI agents to interact with ticketing systems, ERP platforms, document stores, and internal APIs.
• Build MCP servers to expose internal systems as tools for AI agents.
• Partner with stakeholders to identify automation opportunities and prioritize a roadmap based on ROI and feasibility.
• Develop production-grade Python services and jobs, including API clients, data transformations, schedulers, and event-driven handlers.
• Build LLM evaluation frameworks using golden datasets, regression checks, and quality gates.
• Implement observability and tracing to monitor failures, costs, latency, and quality degradation.
• Design human-in-the-loop checkpoints and safe fallbacks where autonomy isn’t appropriate.
• Optimize AI applications for cost and latency via model selection, caching, batching, prompt optimization, and routing.
• Document architecture, runbooks, and operational procedures; support automations post-deployment.
• Ensure AI solutions comply with security, privacy, responsible AI, access-control, and PII requirements.

Skills

Python development

LLM APIs

Agentic AI frameworks

RAG systems

Prompt engineering

MCP servers

REST/GraphQL APIs

SQL

Git/CI/CD

Cloud platforms (AWS/Azure/GCP)

Docker/containerization

Stakeholder management

Education

Bachelor’s degree in Computer Science, Engineering, or related field

Tools

LangChain

LangGraph

LlamaIndex

CrewAI

Semantic Kernel

AutoGen

pgvector

Pinecone

Weaviate

Qdrant

Milvus

OpenSearch

Docker

Job description

Our client is looking for an AI Automation Engineer to design, build, and operate AI-powered automations that reduce manual effort across business and engineering workflows.

This is a hands-on engineering role focused on converting ambiguous, human-in-the-loop processes into reliable, monitored, production-grade automations using LLMs, agentic frameworks, APIs, and workflow orchestration tools.

Minimum Qualifications

• 3–5 years of professional experience in Software Engineering, Data Engineering, or Automation Engineering, including at least 1 year of hands-on LLM/AI experience.
• Strong Python development skills, including API integration, asynchronous programming, testing, packaging, and maintainable code.
• Practical experience using LLM APIs such as OpenAI, Anthropic Claude, Gemini, or Amazon Bedrock in production applications.
• Hands-on experience with at least one agentic AI/orchestration framework, such as LangChain, LangGraph, LlamaIndex, CrewAI, Semantic Kernel, or AutoGen.
• Demonstrated experience building RAG systems using vector stores such as pgvector, Pinecone, Weaviate, Qdrant, Milvus, or OpenSearch.
• Strong understanding of prompt engineering, context design, structured outputs, JSON schemas, tool/function calling, and validation.
• Familiarity with Model Context Protocol (MCP) and building MCP servers to expose internal systems as agent tools.
• Strong experience with REST/GraphQL APIs, OAuth, token-based authentication, webhooks, pagination, and rate-limit handling.
• Working knowledge of SQL and data modeling.
• Experience with Git, code reviews, and CI/CD.
• Cloud experience with AWS, Azure, or GCP, including compute, serverless functions, queues, secrets management, and managed AI services.
• Basic Docker/containerization knowledge.
• Strong stakeholder-management skills, including requirements gathering, prototyping, demonstrations, and expectation management.

Key Responsibilities

• Build and deploy end-to-end AI automations and agentic workflows integrating LLMs with internal systems, APIs, and data sources.
• Design and implement RAG pipelines, including chunking, embeddings, vector search, re-ranking, and grounded response generation.
• Develop tool/function-calling integrations that allow AI agents to interact with ticketing systems, ERP platforms, document stores, and internal APIs.
• Build MCP servers to expose internal systems as tools for AI agents.
• Partner with stakeholders to identify high-value automation opportunities and prioritize an automation roadmap based on ROI and feasibility.
• Develop production-grade Python services and jobs, including API clients, data transformations, schedulers, and event-driven handlers.
• Build LLM evaluation frameworks using golden datasets, regression testing, accuracy checks, hallucination detection, and quality gates.
• Implement observability and tracing to monitor failures, costs, latency, and quality degradation.
• Design human-in-the-loop checkpoints, approval workflows, and safe fallbacks where full autonomy is not appropriate.
• Optimize AI applications for cost and latency through model selection, caching, batching, prompt optimization, and model routing.
• Document architecture, runbooks, and operational procedures and support automations after production deployment.
• Ensure AI solutions comply with security, privacy, responsible AI, access-control, and PII requirements.

Preferred Qualifications

• Experience with workflow automation platforms such as n8n, Zapier, Power Automate, Airflow, Temporal, Prefect, or Dagster.
• RPA experience with UiPath, Automation Anywhere, or Blue Prism.
• Experience with LLM observability and evaluation tools such as LangSmith, LangFuse, Arize, Braintrust, Ragas, or DeepEval.
• Experience designing planner/executor and supervisor architectures.
• Experience with document intelligence, OCR, PDF parsing, table extraction, and multimodal/vision models.
• Frontend experience with React.js, Next.js, or TypeScript.
• Exposure to Terraform, CloudFormation, or Kubernetes.
• Experience with enterprise AI governance, including audit trails, data residency, AI risk reviews, and access-scoped retrieval.
• Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience.