Job Description

If you thrive building at the intersection of production APIs, RAG, multi-agent frameworks, and LLM evaluation, this role is for you.

The role focuses on engineering, optimizing, and evaluating production-grade AI systems for an AI Chat platform. You'll work across GenAI workflows, autonomous agents, retrieval systems, backend integrations, and evaluation frameworks to build AI solutions that are reliable, scalable, and ready for real-world use.

Key Responsibilities

Build, tune, and deploy robust GenAI workflows, autonomous agents, and RAG pipelines.
Design and optimize multi-agent workflows for complex customer use cases.
Develop automated evaluation frameworks to measure LLM accuracy, hallucinations, relevance, reliability, and performance.
Integrate AI applications with backend services, APIs, databases, and enterprise systems.
Work with Python or Java, PostgreSQL, Vector Databases, LibreChat, and Model Context Protocol (MCP).
Develop and refine prompt strategies, retrieval pipelines, context management, and agent workflows.
Troubleshoot and optimize complex end-to-end AI pipelines for performance, scalability, and reliability.
Investigate issues across models, APIs, retrieval systems, orchestration layers, and backend services.
Build mechanisms for monitoring and evaluating AI systems in production.
Collaborate with engineering and product teams to turn AI capabilities into reliable customer-facing solutions.

Required Skills

4–8 years of experience in software development, systems engineering, or AI engineering.
Strong programming fundamentals in Python or Java.
Hands-on experience building or integrating Generative AI and LLM-based applications.
Strong understanding of RAG architectures and Vector Databases.
Practical experience with Agentic AI, autonomous agents, or multi-agent frameworks.
Experience with Prompt Engineering, LLM evaluation, and LLMOps.
Strong API integration and backend development experience.
Good understanding of PostgreSQL or similar relational databases.
Strong debugging and problem-solving skills.
Ability to troubleshoot complex, end-to-end AI workflows.

Good to Have

Experience with LibreChat or comparable AI chat platforms.
Experience with Model Context Protocol (MCP).
Exposure to LangChain, LlamaIndex, or similar agent frameworks.
Experience in Cybersecurity, Networking, IoT/OT, or Security Products.
Experience building high-throughput, production-grade AI systems.
Familiarity with AI observability, evaluation pipelines, and reliability engineering.

The Technical Scope

This role sits at the intersection of software engineering and production AI.

You'll work across LLMs, RAG, agentic workflows, APIs, vector search, backend systems, and automated evaluation. The focus extends beyond integrating AI models to building systems that can perform reliably at scale and deliver measurable outcomes.

This is an opportunity for engineers who enjoy working through complex systems problems and turning emerging AI capabilities into robust production workflows.

Build the Next AI Workflow

Work across GenAI, RAG, multi-agent systems, APIs, and LLM evaluation.

Bengaluru

[Confidential Information]