Senior AI Engineer

Milestone Technologies; Hyderabad; On-site; INR 2,500,000 - 4,500,000; Full time

Job summary

Milestone Technologies seeks an experienced AI/ML engineer to drive Forward Deployed Engineering for client-facing feature suites. You will build and adapt RAG and GraphRAG-based solutions, integrate with enterprise systems, and align field feedback with production deployments.

You will collaborate with product, data, and engineering teams to translate field requirements into reliable AI-enabled capabilities, including orchestration, vector stores, and data pipelines, in enterprise contexts.

Qualifications

• 5+ years hands-on AI/ML or backend engineering with Python.
• Experience building GenAI/LLM apps using RAG, GraphRAG, embeddings and vector stores.
• Experience integrating AI features with enterprise systems, APIs, data pipelines and orchestration layers.
• Comfort with Forward Deployed Engineering including client-facing discovery and prototyping.
• Familiarity with LangGraph, LangChain, MCP-based integrations.
• Ability to validate AI outputs using golden datasets and grounding criteria.
• Strong communication to explain trade-offs to technical and business stakeholders.

Responsibilities

• Develop and configure AI-enabled features across client-facing capability suites.
• Implement RAG, GraphRAG, prompt workflows and retrieval pipeline integrations.
• Translate field requirements into deployable technical solutions with stakeholders.
• Build dynamic query-generation and graph-aware retrieval for knowledge graphs.
• Integrate AI with backend APIs, vector stores, data sources and platform services.
• Validate outputs against golden datasets and acceptance criteria.
• Support field deployment, troubleshooting, demos, and production readiness.
• Document solution behavior, assumptions, and upgrade paths.

Skills

AI/ML engineering

GenAI/LLM applications

RAG/GraphRAG

Python

Enterprise integration

Forward Deployed Engineering

Agent frameworks (LangGraph, LangChain

Tools

LangGraph

LangChain

MCP-based integrations

Job description

Role summary

Implements AI and Forward Deployed Engineering capabilities across client-facing feature suites, combining hands-on GenAI engineering with solution deployment, integration, configuration, and field feedback loops. The role focuses on building and adapting RAG, GraphRAG, agentic workflows, orchestration integrations, and data-connected AI features so they work reliably in real enterprise environments.

Key responsibilities

• Develop and configure AI-enabled features across assigned client-facing capability suites
• Implement RAG, GraphRAG, prompt workflows, agent routing, and retrieval pipeline integrations
• Work directly with product, business, data, and engineering stakeholders to translate field requirements into deployable technical solutions
• Build dynamic query-generation and graph-aware retrieval capabilities for knowledge-graph-backed use cases
• Integrate AI capabilities with backend APIs, orchestration services, vector stores, enterprise data sources, and platform services
• Validate outputs against golden datasets, acceptance criteria, grounding rules, and enterprise quality expectations
• Support field deployment, configuration, troubleshooting, demos, UAT feedback, and production-readiness activities
• Document solution behavior, deployment assumptions, known limitations, and upgrade paths for future releases

Required skills & experience

• 5+ years hands-on AI, ML, data, backend, or solution engineering experience, with strong Python fundamentals
• Practical experience building GenAI / LLM applications using RAG, GraphRAG, prompt engineering, embeddings, and vector stores
• Experience integrating AI features with enterprise systems, APIs, data pipelines, orchestration layers, or workflow platforms
• Comfortable working in a Forward Deployed Engineering model, including client-facing discovery, rapid prototyping, field configuration, issue triage, and stakeholder demos
• Familiarity with agent frameworks such as LangGraph, LangChain, MCP-based integrations, or comparable orchestration patterns
• Ability to validate AI outputs using golden datasets, regression checks, grounding criteria, and measurable acceptance criteria
• Strong communication skills with the ability to explain technical trade-offs, implementation constraints, risks, and field observations to technical and business stakeholders

Preferred qualifications

Experience delivering AI solutions in regulated, enterprise, healthcare, pharma, manufacturing, or data-governed environments