We are looking for a Mid-Senior Applied AI Engineer to design, develop, and deploy scalable AI solutions within an enterprise AI platform. This role goes beyond basic implementation and requires strong architectural thinking to build robust GenAI services, advanced RAG pipelines, and agentic workflows.
The ideal candidate will work closely with AI Program Managers, Data & Analytics teams, and business stakeholders to translate business requirements into secure, production-ready AI applications.
Key Responsibilities
Platform Development
Design and build scalable AI application components supporting enterprise AI initiatives
Develop agentic workflows, batch processing systems, and enterprise data integrations
Advanced Retrieval & Agentic Architectures
Implement and optimize embeddings and vector search strategies
Build sophisticated RAG pipelines for structured and unstructured enterprise data
Develop multi-agent orchestration workflows
API & Backend Engineering
Build secure, high-performance backend APIs using Python and FastAPI
Integrate enterprise AI services with foundational models and internal systems
Model Integration & Orchestration
Work with LLMs such as OpenAI, Claude, and Gemini through model-agnostic routing layers
Optimize model usage for latency, cost, and performance
Feasibility & Solution Design
Collaborate with AI Program Managers and Business Analysts during project intake
Assess technical feasibility, architecture requirements, and data readiness
Deployment & LLMOps
Drive deployment of AI systems using Docker and CI/CD pipelines
Establish monitoring, observability, prompt evaluation, and accuracy tracking
Governance & Compliance
Ensure compliance with enterprise AI governance, security, and data privacy standards
Mentorship
Provide technical guidance and code reviews for junior engineers
Required Skills & Technologies
AI Models
Hands-on experience with at least ONE of the following:
OpenAI
Anthropic (Claude)
Google Gemini
AI Frameworks
Hands-on experience with at least ONE of the following:
LangChain
LangGraph
LlamaIndex
Azure AI Search
Backend & APIs
Strong Python programming skills
Experience with FastAPI
Basic Node.js knowledge preferred
Data & Vector Search
Experience with Vector Databases such as:
Azure AI Search
Pinecone
Milvus
Experience with PostgreSQL or relational databases
Cloud & DevOps
Azure Cloud / Azure AI Services
Git, Docker, CI/CD
LLM observability tools preferred
Preferred Experience
Experience designing enterprise-grade RAG systems
Experience with embeddings, chunking, vector indexing, and retrieval optimization
Experience building agentic AI workflows
Familiarity with multimodal AI/OCR pipelines
Exposure to prompt engineering and hallucination mitigation techniques
Pay: ₹456,315.99 - ₹1,753,678.59 per year
Benefits:
- Cell phone reimbursement
- Flexible schedule
- Food provided
- Paid time off
- Provident Fund
Work Location: Hybrid remote in Pune, Maharashtra (Pune, 411046)
