AI Engineer

Job Title

Full-stack Associate

Job Description

We are looking for a full-stack associate to design, configure, and deploy AI agents and intelligent automation solutions on an enterprise-grade Automation Anywhere GenAI platform while leveraging RAG (Retrieval-Augmented Generation) as the knowledge foundation for the Automation Anywhere Enterprise Knowledge Base (EKB). Full-stack knowledge of candidate will be used to integrate upstream full stack bots/APIs and downstream AAA Enterprise RPA Gen1, Gen2 (DocAI), and Gen3 (GenAI) bots, and vice versa. The Associate will define RAG success criteria (retrieval accuracy, hallucination thresholds) and KPIs; inventory knowledge sources (documents, databases) as an Enterprise Knowledge Base. Data sourcing plan and design end-to-end Agent flows covering triggers, KB retrieval, LLM calls, and actions. KB structure (chunking, fine-tuning) will be defined and built using EKB. Prototype prompts and Agents will be developed to produce functional test Chat/Agent prototypes. Agents and Prompts will be configured with a selected LLM (Gemini/GPT-4) to generate Agent configurations and prompt templates. Downstream API tasks (RPA steps/external calls) will be integrated, followed by UAT deployment (publish Agent/KB). Upon successful UAT, the solution will be published to Production via the Production Control Room, with BOT/Agent monitoring as part of Hypercare.

Qualifications

Education: Bachelor's or Master's in Computer Science, AI/ML, Data Science, or equivalent practical experience. Experience: 1-3 years in software engineering; 1+ years building AI-powered automation solutions in production. Certifications (Preferred): Cloud AI certifications (AWS, Azure, GCP); RPA certifications such as UiPath or Automation Anywhere. Scope & Growth Path: Implement designs under Senior Engineer guidance; progress toward independent stakeholder ownership.

Agentic AI

Hands-on experience with LangChain, LangGraph, AutoGen, or CrewAI. Core agent patterns: tool usage, memory, multi-step reasoning, validation and guardrails. LLM APIs: OpenAI, Anthropic, Gemini, or open-source models; structured prompt engineering.

RAG & Vector Infrastructure

End-to-end RAG pipelines: ingestion, chunking, embedding, vector stores, and retrieval evaluation. Hands-on with vector databases; ability to diagnose and improve retrieval quality.

RPA

Hands-on with UiPath, Automation Anywhere, or Microsoft Power Automate. Bot workflows with exception handling, logging, and enterprise system integrations.

Engineering

Strong Python skills; experience with cloud AI services, APIs, data pipelines, and event-driven systems.

Nice to Have

Exposure to LoRA / QLoRA fine-tuning approaches. Agent observability and evaluation tooling such as LangSmith or Arize.

Responsibilities

Build and maintain multi-agent workflows from solution design through production deployment. Implement root-cause analysis, ERP/CRM/ITSM integrations, and robust error handling. Design and operate end-to-end RAG systems; continuously monitor and improve retrieval quality. Develop and maintain RPA tasks; integrate AI agents with RPA and business logic. Write unit and integration tests; contribute to CI/CD pipelines and deployment automation. Collaborate with senior engineers; document pipelines, agent configurations, and operational runbooks.