GenAI / Agentic AI Developer

The ideal candidate has experience designing, developing, and deploying enterprise-grade GenAI solutions that integrate AI agents, APIs, enterprise data sources, vector databases, and cloud platforms. This role requires strong Python development skills combined with practical experience building production-ready AI applications.

Key Responsibilities

• Design and develop GenAI applications using LLMs, RAG, agent frameworks, and tool-calling architectures.
• Build and orchestrate multi-agent workflows including planner, retriever, executor, validator, and human-in-the-loop agents.
• Develop scalable backend services using Python, FastAPI, Flask, REST APIs, and microservices.
• Implement document ingestion, embeddings, vector search, reranking, and retrieval pipelines.
• Integrate AI solutions with enterprise applications, APIs, databases, knowledge bases, and document repositories.
• Deploy and support GenAI applications using Docker, Kubernetes, CI/CD, and cloud-native services.
• Implement monitoring, evaluation, logging, prompt management, and LLMOps best practices.
• Collaborate with business and technical stakeholders to deliver measurable business value through AI solutions.

Required Qualifications

• 5+ years of hands-on Python development experience.
• Experience building and deploying GenAI or Agentic AI applications.
• Hands-on experience with one or more of the following:
  • LangGraph
  • LangChain
  • AutoGen
  • CrewAI
  • Semantic Kernel
  • LlamaIndex
• Strong understanding of:
  • Retrieval-Augmented Generation (RAG)
  • Embeddings
  • Vector databases
  • Semantic search
  • Prompt engineering
• Experience with one or more vector platforms:
  • OpenSearch
  • Pinecone
  • Chroma
  • FAISS
  • Weaviate
  • Milvus
  • Azure AI Search
  • pgvector
• Experience with Azure OpenAI, AWS Bedrock, OpenAI, Anthropic Claude, Gemini, Llama, or similar platforms.
• Experience developing REST APIs and cloud-native applications.

Preferred Qualifications

• Multi-agent orchestration and autonomous workflow design.
• GraphRAG, MCP, Neo4j, knowledge graphs, or entity extraction.
• LLMOps tools such as:
  • LangSmith
  • MLflow
  • Phoenix
  • Ragas
  • TruLens
  • Arize
• Experience with:
  • Azure AI Foundry / Azure OpenAI
  • AWS Bedrock / SageMaker
  • Google Cloud Platform Vertex AI
• Knowledge of AI security, guardrails, prompt injection prevention, responsible AI, and PII protection.

Required Interview Discussion

Candidates must be able to clearly articulate at least one end-to-end GenAI or Agentic AI project, including:

• Business problem
• Solution architecture
• LLMs and frameworks used
• RAG and retrieval strategy
• Deployment approach
• Evaluation methodology
• Business outcomes and impact