Job Summary :

We are looking for a highly skilled Senior Consultant Agentic AI & Web Data Engineer with strong expertise in Python, AWS Bedrock, LLM agents, web crawling, and intelligent data extraction.

The ideal candidate will design and develop production-grade Agentic AI solutions using AWS Bedrock, LangChain/LangGraph, and Claude, while also building resilient web data acquisition and document extraction pipelines.

The role requires strong engineering fundamentals and an ability to design deterministic-first, LLM-second pipelines, using traditional software techniques wherever they provide greater reliability, accuracy, and predictability.

Key Responsibilities :

Agentic AI & LLM Engineering :

- Design and develop production-ready Agentic AI applications and LLM-powered workflows using AWS Bedrock.

- Build intelligent agents and multi-step workflows using LangChain and LangGraph.

- Integrate and orchestrate Claude and other LLM models through AWS Bedrock.

- Design agent workflows involving tool calling, state management, context handling, validation, and error recovery.

- Implement appropriate guardrails, retries, fallbacks, and output validation mechanisms.

- Develop reliable AI pipelines following a deterministic-first, LLM-second architecture.

- Evaluate and optimize LLM applications for accuracy, latency, scalability, reliability, and cost.

- Stay current with emerging developments in Agentic AI, LLM frameworks, and AI engineering.

Python & AWS Engineering :

- Develop scalable and maintainable backend applications using Python.

- Build integrations with AWS services using boto3.

- Implement secure AWS authentication and authorization using AWS STS and IAM.

- Design cloud-native solutions with appropriate security, scalability, observability, and fault tolerance.

- Develop APIs and services required to support AI agents and data processing pipelines.

- Perform performance optimization, debugging, and production issue resolution.

Web Crawling & Data Engineering :

- Design and implement resilient web crawling and data acquisition pipelines.

- Develop crawlers using httpx, Playwright, and related Python technologies.

- Handle dynamic web applications, JavaScript-rendered content, pagination, retries, timeouts, rate limits, and session management.

- Work with robots.txt and sitemaps to identify and efficiently navigate publicly available web content.

- Build robust mechanisms for content discovery, extraction, normalization, deduplication, and validation.

- Design crawling systems that can handle changes in website structure and temporary failures.

- Ensure crawling implementations respect applicable website policies, access restrictions, and legal requirements.

PDF & Document Extraction :

- Design and implement content-anchored PDF extraction solutions.

- Extract structured and semi-structured information from complex PDF documents.

- Combine deterministic parsing techniques with LLM-based extraction where appropriate.

- Implement validation and confidence checks to improve extraction accuracy.

- Handle different document layouts, tables, sections, and content structures.

Architecture & Engineering Excellence :

- Design scalable, reliable, maintainable, and production-grade data and AI solutions.

- Establish appropriate boundaries between deterministic processing and LLM reasoning.

- Write clean, modular, reusable, and testable Python code.

- Develop unit, integration, and functional tests for AI, crawling, and extraction workflows.

- Participate in architecture reviews, code reviews, technical discussions, and solution design activities.

- Mentor junior engineers and contribute to technical best practices.

- Troubleshoot complex engineering challenges and perform root-cause analysis.