FDE - Agentic Ai

Qualification: BTech/MTech/MCA
Mode of Work: Hybrid

•     Embed with customer engineering teams: Understand the customers business processes, technical architecture and operational constraints. Turn ambiguous business problems into scalable, AI-enabled production systems.

•     Build production AI applications: Design and develop production-grade software for AI and agentic workflows, including multi-agent orchestration, retrieval pipelines, workflow automation and decision intelligence. Integrate foundation models, customer data sources, APIs and existing applications into cohesive AI experiences. Optimize for latency, reliability, observability, cost and security.

•     Own production: Take systems from design through production rollout and ongoing operations. Troubleshoot incidents across AI models, distributed systems, data pipelines and application services. Put in place monitoring, evaluations, guardrails, testing, CI/CD, rollback and resiliency mechanisms that keep AI systems healthy at scale.

•     Accelerate customer transformation: Identify opportunities to expand AI adoption across customer workflows. Build reusable patterns, accelerators and reference architectures for future engagements.

•     Raise the bar: Mentor engineers and contribute to engineering best practices for AI and forward deployment. Feed reusable components and learnings back into products and services.

Requirements

• Python: Strong, production-grade Python — clean code, testing, APIs, and integration with enterprise systems.
  
• Agentic AI on AWS: Hands-on experience building multi-agent systems on Amazon Bedrock and Bedrock AgentCore, including:
  
• Prompt engineering
  
• Tool calling
  
• Agent orchestration with a framework (e.g., Strands Agents, LangGraph, LangChain)
  
• RAG & Retrieval: Building retrieval pipelines, including:
  
• Embeddings
  
• Chunking
  
• Vector search (e.g., Bedrock Knowledge Bases, OpenSearch, pgvector)
  
• Core AWS Services: Working knowledge of:
  
• Serverless and container services (e.g., Lambda, ECS/EKS)
  
• API Gateway
  
• Storage (e.g., S3, DynamoDB)
  
• Security and networking (e.g., IAM)
  
• Production Engineering: Experience taking AI systems to production, including:
  
• CI/CD
  
• Automated testing
  
• Monitoring
  
• Evaluations and guardrails for AI output
  

Benefits