Senior AI Engineer

This position is listed on behalf of a partner company, who manages all applications and next steps. We are seeking an experienced Senior AI Engineer (Python) based in India.

Develop, enhance, and maintain AI agents and orchestration capabilities using Python, LangGraph, and LangChain. Build and extend AI-enabled guided workflows, intelligent automation solutions, and enterprise AI capabilities.

Design, implement, and optimize conversational AI applications and chat-based user experiences. Develop agent planning, state management, orchestration, memory, tool-calling, and response-generation capabilities.

Integrate AI agents and applications with enterprise platforms, backend services, APIs, and external tools. Support modern AI integration frameworks and agent communication patterns to enable reliable interactions between AI systems.

Implement AI observability, monitoring, telemetry, evaluation, and performance-tracking capabilities.

Collaborate with engineering teams and business stakeholders to define technical approaches and deliver AI-powered business use cases.

Troubleshoot complex technical issues, strengthen application reliability, and optimize system performance.

Contribute to architecture discussions, engineering standards, reusable components, testing practices, and scalable AI development methodologies.

Support the continuous improvement of enterprise AI platform capabilities, ensuring solutions remain maintainable, secure, and production-ready.

At least 8 years of hands-on experience in Python development and enterprise application engineering.

At least 2 years of practical experience with LangGraph, including agent workflows, stateful orchestration, multi-agent systems, and AI-driven execution flows.

At least 2 years of experience with LangChain, including LLM-powered applications, tool integrations, retrieval-augmented generation (RAG), and workflow automation.

Strong understanding of agentic AI concepts, including intelligent agents, planning, orchestration, memory management, and tool-calling frameworks.

Demonstrated experience building, deploying, and maintaining production-grade Generative AI applications.

Experience integrating AI solutions with enterprise platforms, backend services, and APIs.

Practical experience designing and delivering conversational AI and chat-based applications for production environments.

Familiarity with AI observability, monitoring, telemetry, model evaluation, and performance analysis tools.

Strong knowledge of software engineering principles, automated testing, debugging, code quality, and performance optimization.

Experience working in Agile development environments and collaborating effectively with cross-functional teams.

Excellent analytical and problem-solving abilities, with strong communication skills and the confidence to engage technical and business stakeholders.

Ability to navigate complex technical challenges, take ownership of deliverables, and contribute to architectural decisions.

Nice-to-have Qualifications: Hands-on experience with Model Context Protocol (MCP) and Agent-to-Agent (A2A) communication.

Experience deploying and maintaining multi-agent AI solutions in production environments.

Knowledge of RAG architectures, enterprise knowledge systems, vector databases, and semantic search technologies.

Familiarity with cloud platforms such as Microsoft Azure, Amazon Web Services (AWS), or Google Cloud Platform (GCP).

Experience contributing to centralized AI platforms that support multiple business functions and use cases.

Exposure to healthcare or other highly regulated enterprise environments.