Role: Senior Tech Mobile Agentic AI Developer

Job ID: DOX1JP00011578

Employment Type: Contract

Experience: 10+ Years

Work Mode: Onsite – Client Interview and Worksite

Role Overview

We are looking for an experienced AI/ML Developer to design, develop, and deploy production-ready Agentic AI solutions that support field technicians. The role focuses on building LLM-powered agents, multi-agent orchestration systems, and advanced Retrieval-Augmented Generation (RAG) pipelines. The ideal candidate will have strong Python development skills, hands-on experience with LLM frameworks, and expertise in building scalable, reliable AI applications for real-world use cases.

Job Duties and Responsibilities

• Design and develop LLM-powered agents using LangGraph and LangChain frameworks.
• Build and enhance multi-agent orchestration pipelines with conditional routing, state management, and error recovery.
• Develop RAG pipelines with hybrid search (semantic and keyword), re-ranking, and Reciprocal Rank Fusion.
• Implement tool-calling agents with parallel API execution, sequential enrichment chains, and summarization.
• Build real-time streaming capabilities using WebSocket and Server-Sent Events (SSE) for conversational AI.
• Integrate with Azure OpenAI APIs using circuit breaker patterns and fallback chains.
• Implement prompt engineering and dynamic prompt management using database-backed storage and in-memory caching.
• Design and implement multimodal AI features, including image analysis using vision models.
• Write production-quality Python code with error handling, logging, observability, and unit tests.
• Participate in code reviews, architecture discussions, and sprint delivery.

Required Qualifications

Must-Have Skills

• 10+ years of software development experience, with strong Python expertise in production environments.
• 2+ years of hands-on LLM development experience using LangChain, LangGraph, or equivalent frameworks.
• Experience developing RAG pipelines, including embeddings, vector search, re-ranking, and answer generation.
• Experience with LLM APIs, including OpenAI Chat Completions, Responses API, streaming, and tool calling.
• Strong asynchronous Python development skills using asyncio, httpx, and FastAPI.
• Prompt engineering expertise, including system prompts, few-shot prompting, and structured JSON output.
• Experience with circuit breaker patterns, retry logic, and resilient service design.
• Experience with PostgreSQL and asynchronous ORMs, including SQLAlchemy Async and Alembic.
• Familiarity with Git, CI/CD, Docker, and Kubernetes fundamentals.
• Strong system design skills covering microservices, distributed systems, and API design.

Nice-to-Have Skills

• Experience with LangGraph StateGraph, including conditional edges, node pipelines, and compiled graphs.
• Knowledge of multi-agent systems, orchestration, routing, and role-based access control (RBAC).
• Experience with Langfuse or similar LLM observability tools for tracing, token usage, and latency monitoring.
• Experience with WebSocket and SSE streaming protocols.
• Knowledge of multimodal AI, vision models, and image analysis.
• Experience with vector databases such as OpenSearch, Pinecone, and pgvector.
• Familiarity with AWS services, including Aurora PostgreSQL, SSM, IAM, and EKS.
• Telecommunications or field service domain experience.