Senior AI Engineer – Agentic AI & Backend

Experience: 5+ Years
Location: Bangalore
Work Mode: Hybrid
Employment Type: Full-time
About the Role
We are looking for a Senior AI Engineer to design, develop, and operate production-ready AI systems powered by LLMs and intelligent agents.
You will be responsible for building the engineering foundation behind AI agents, MCP-based integrations, agentic workflows, and AI-powered connectors. The role involves taking solutions from architecture and development through deployment, monitoring, evaluation, and continuous improvement.
This is a hands-on engineering position, not a research or prompt-engineering role. You should enjoy solving complex engineering problems and building reliable AI applications that can operate at scale.
Key Responsibilities
- Design and develop MCP servers that allow AI agents to securely access data, APIs, and business capabilities.
- Build robust agentic workflows involving tool calling, orchestration, multi-step execution, and human approval when required.
- Develop integrations that connect AI agents with external applications, platforms, and enterprise systems.
- Own services throughout their lifecycle, including architecture, development, deployment, monitoring, and production support.
- Establish evaluation processes to measure agent accuracy, reliability, and behavioral consistency.
- Implement logging, tracing, and observability to understand and troubleshoot AI-agent behavior.
- Improve systems for performance, latency, cost efficiency, scalability, and reliability.
- Create reusable SDKs, frameworks, and engineering components for AI development.
- Work closely with Product, Design, Engineering, and customer-facing teams to convert requirements into production solutions.
- Evaluate emerging technologies across the rapidly evolving LLM and agent ecosystem.
Required Qualifications
- 5+ years of software engineering experience with experience delivering production systems.
- Strong hands-on expertise in Python backend development.
- Proven experience developing and deploying LLM-powered applications or AI agents.
- Practical knowledge of:
- Function/tool calling
- Structured outputs
- Prompt chaining
- Agent orchestration
- Multi-agent systems
- Human-in-the-loop workflows
- Experience developing MCP servers or equivalent AI integrations/tool interfaces.
- Understanding of LLM evaluation and testing methodologies.
- Experience deploying applications using AWS, GCP, or similar cloud platforms.
- Good knowledge of Docker and containerized applications.
- Experience with asynchronous programming in Python.
- Strong understanding of APIs, backend architecture, and distributed services.
- Ability to make sound technical decisions while keeping the end-user and business requirements in mind.
Preferred Skills
- Experience with LangGraph, LangChain, Anthropic SDK, Pydantic-AI, CrewAI, or similar agent frameworks.
- Familiarity with AI observability and tracing platforms such as Langfuse, LangSmith, or OpenTelemetry.
- Exposure to LLMOps, agent evaluation, and AI monitoring.
- Experience with digital analytics, application monitoring, APM, or observability platforms.
- Contributions to open-source AI/engineering projects, technical blogs, presentations, or community initiatives are a plus.

Work arrangement
No