Job Description

Role: Senior AI Software Engineer (Agentic AI / AI Agents)
Location: Hybrid
Duration: 12+ Months

Interview: In-Person

We are seeking a hands-on Senior AI Software Engineer with strong experience in designing, building, and deploying production-grade Agentic AI systems The ideal candidate should have expertise in developing AI Agents capable of multi-step reasoning, tool orchestration, Retrieval-Augmented Generation (RAG), and secure enterprise AI solutions.

This is NOT a traditional Java/.NET Full Stack or chatbot integration role. We are specifically looking for engineers with real-world production experience building AI Agents using Python and modern Agentic AI frameworks

Required Skills

• 5–10+ years of Software Engineering experience.
• Strong hands-on experience with Python and backend development ( FastAPI preferred).
• Experience building and deploying production AI Agents / Agentic AI applications
• Strong experience with LangGraph, LangChain, CrewAI, AutoGen or similar AI Agent frameworks.
• Hands-on experience with:
  • Retrieval-Augmented Generation (RAG)
  • AI Agent Architecture
  • Multi-Agent Systems
  • Tool Calling / Function Calling
  • Agent Memory
  • Prompt Engineering
  • Embeddings
• Experience with Vector Databases such as Pinecone, FAISS, Weaviate, ChromaDB, or Azure AI Search
• Experience deploying LLM applications using OpenAI, Azure OpenAI, AWS Bedrock, Anthropic Claude, Google Vertex AI, or Llama models
• Strong experience with Docker, Kubernetes, CI/CD, LLMOps, Monitoring & Observability
• Experience working on AWS, Azure, or GCP
• Strong understanding of AI Security, Guardrails, Prompt Injection Protection, PII Handling, RBAC, and Responsible AI.

Responsibilities

• Design and develop enterprise-scale Agentic AI solutions.
• Build AI Agents capable of planning, reasoning, tool usage, and multi-step task execution.
• Develop reusable AI Agent frameworks, SDKs, and RAG pipelines.
• Build secure AI services with proper guardrails, approval workflows, retries, and fault tolerance.
• Implement production LLMOps, monitoring, evaluation, observability, and performance optimization.
• Collaborate with Product Managers, Data Scientists, and Engineering teams to deliver scalable AI platforms.

Preferred Experience

• LangGraph
• MCP (Model Context Protocol)
• AI Agent Evaluation Frameworks
• Healthcare, Banking, Insurance, or other regulated industry experience

Additional Information

All your information will be kept confidential according to EEO guidelines.