Description

What You'll Do:

• Design and develop backend AI services, APIs, orchestration layers, and integration components using TypeScript, Python, and Node.js.
• Build scalable backend services supporting AI Agents, Copilots, Assistants, and workflow automation platforms.
• Develop REST APIs, asynchronous services, event-driven workflows, background jobs, queues, WebSocket, and SSE streaming services.
• Design robust service architectures that support enterprise-scale AI workloads.
• Build and implement Agentic AI workflows using LangChain, LangChain.js, LangGraph, MCP SDK, Semantic Kernel, CrewAI, AutoGen, OpenAI-compatible APIs.
• Develop intelligent agent capabilities including Tool Calling, Function Calling, Task Planning, Workflow Orchestration, Memory Management, Structured Outputs, Execution Monitoring, Error Recovery Mechanisms.
• Design graph-based workflow automation and multi-agent systems.
• Integrate cloud and on-premise LLMs including OpenAI Models, Qwen, DeepSeek, GLM, Other Enterprise-Approved Models.
• Implement prompt engineering strategies and model optimization techniques.
• Develop secure and scalable AI-powered applications and services.
• Evaluate and improve LLM response quality and system performance.
• Design and implement Model Context Protocol (MCP) integrations.
• Develop MCP client and server implementations.
• Manage using Tool Registration, Access Controls, Permissions Management, Service Onboarding, Logging & Monitoring, Secure Connectivity.
• Integrate AI systems with enterprise applications and business workflows.
• Build enterprise-grade RAG pipelines.
• Develop Document Parsing, Chunking Strategies, Embedding Pipelines, Vector Search Frameworks, Knowledge Ingestion Pipelines, Retrieval Evaluation Mechanisms.
• Improve knowledge quality, retrieval accuracy, and contextual reasoning capabilities.
• Integrate AI systems with structured and unstructured enterprise knowledge sources.
• Design semantic data structures supporting AI reasoning and intelligent workflows.
• Build and maintain Knowledge Graphs, Metadata Models, Ontologies, Taxonomies, Entity Relationships, Graph Databases.
• Implement hybrid Graph + Vector Search architectures.
• Enable advanced semantic search and contextual AI capabilities.
• Design and deploy cloud-native AI applications using AWS services.
• Build containerized workloads using Docker and Kubernetes.
• Implement CI/CD pipelines and deployment automation.
• Develop scalable and resilient infrastructure supporting AI workloads.
• Automate system provisioning, monitoring, and operational processes.
• Implement monitoring, logging, and observability capabilities.
• Build OpenTelemetry Instrumentation, Distributed Tracing, Performance Monitoring,  Cost Tracking, AI Evaluation Frameworks.
• Monitor model performance, latency, reliability, and operational health.
• Troubleshoot production issues and optimize system performance.
• Collaborate with AI Product Owners, Data Scientists, Software Engineers, Application Scientists, QA Teams, Support Teams, Business Stakeholders.
• Participate in solution design workshops and architecture discussions.
• Contribute to technical standards and engineering best practices.
• Mentor junior engineers and support knowledge-sharing initiatives.

Expertise You'll Bring:

• Experience working with laboratory, scientific, or automation environments.
• Knowledge of Knowledge Graph technologies.
• Experience with OpenTelemetry and observability platforms.
• Exposure to MLOps and AI model lifecycle management.
• Familiarity with multi-tenant architectures and SaaS platforms.
• Experience implementing AI governance and security controls.
• Knowledge of distributed systems and high-availability architectures.
• Strong experience with TypeScript, Node.js, Python.
• Expertise in asynchronous programming and backend service development.
• Strong understanding of REST APIs, WebSockets, Server-Sent Events (SSE), Event-Driven Architectures, Microservices.
• Hands-on experience with LangChain, LangChain.js, LangGraph, MCP SDK, LlamaIndex, Semantic Kernel, CrewAI, AutoGen.
• Experience building AI Agents, AI Assistants, Copilots, Workflow Automation Solutions.
• Strong understanding of Large Language Models (LLMs), Prompt Engineering, Tool Calling, Structured Outputs, Memory Management, Agent Orchestration, AI Evaluation.
• Experience integrating OpenAI-compatible models and enterprise AI platforms

Key Skills

Education

Any Graduate