Software Engineer III - Agentic AI

Overview

Lead the design and delivery of multi-agent systems on the Agora Orchestrator platform at MRI Software, including architecture, MCP server authoring, RAG system design, and setting engineering standards for the team.

What you'll do

• Design and implement multi-agent orchestration using LangGraph (state, checkpointing, human-in-the-loop).
• Author MCP servers: tool schemas, auth, error contracts, versioning.
• Architect RAG systems: retrieval strategy, reranking, hybrid search, evaluation.
• Build and maintain the agent evaluation and observability stack.
• Deploy and operate agents on Azure Foundry Agent Service and Azure Functions.
• Establish agentic patterns and reference implementations for the team.
• Mentor junior engineers and lead technical design reviews.

What you'll need

• Python (expert): async, typing, packaging, performance.
• LangGraph in production: multi-agent orchestration, state management, checkpointing, human-in-the-loop.
• LangChain (tools, retrievers, callbacks) and FastAPI (async, auth, streaming).
• Azure Foundry Agent Service (provisioning, threads, tool wiring) and Azure Functions.
• AI agentic orchestration and agentic patterns: planner/executor, supervisor, reflection, tool use, multi-agent collaboration.
• MCP server design and authoring: tool schemas, auth, error contracts, versioning.
• RAG architecture: retrieval strategy, hybrid search, reranking, evaluation.
• Prompt engineering with structured eval frameworks (LangSmith, Promptfoo, or equivalent).
• Agent observability: tracing, App Insights, token/cost telemetry, failure-mode analysis.
• ML / Python libraries: PyTorch, Hugging Face Transformers, sentence-transformers, scikit-learn, NumPy, Pandas.
• Identity: Okta, OAuth2, JWT (client_id propagation, scopes).
• System design: multi-tenant SaaS, idempotency, retries, queueing.
• 5+ years building software in Python.
• 2+ years building production LLM or agentic systems.
• Track record of leading technical design and mentoring engineers.
• Bachelor's/master's degree in software engineering, Computer Science, or a related area.

Nice to have

• Azure Agent Framework (Python).
• Fine-tuning (SFT/LoRA), model routing, cost/latency optimization, semantic caching.
• Pydantic, DSPy, or similar typed/optimized agent frameworks.
• Angular or React for Agent / Workflow Studio surfaces.
• Azure DevOps or GitHub Actions, Bicep / Terraform IaC.
• PostgreSQL, SQL Server, semantic layer / dataset definition design.

Details

• Location: Baroda, India (Office).
• Hybrid working arrangements.
• Annual performance-related bonus.
• 6x Flexi Anyday: knock 2.5 hours off your day.
• Medical insurance coverage for extended family members.