About the Company
We are seeking a forward thinking AI Engineer to architect and deploy intelligent systems powered by Large Language Models (LLMs), Retrieval Augmented Generation (RAG), and advanced chunking strategies. This role is ideal for engineers passionate about building scalable production grade AI applications that leverage cutting edge retrieval and generation techniques.
About the Role
This role involves designing and implementing RAG pipelines, applying chunking strategies, building multiagentic systems, integrating AI capabilities into enterprise applications, and ensuring model reliability and ethical compliance across deployments.
Responsibilities
- Design and implement RAG pipelines using hybrid search, vector, keyword, semantic ranking, and metadata enrichment.
- Apply chunking strategies (fixed-size, recursive, semantic, agentic) to optimize document segmentation for retrieval and embedding.
- Build multiagentic systems.
- Integrate AI capabilities into enterprise applications using Azure OpenAI, Azure Search, Azure Functions, CoPilot Studio, and Power Automate.
- Collaborate with stakeholders to translate business needs into scalable AI solutions.
- Ensure model reliability, performance, and ethical compliance across deployments.
- Coordinate and manage the Offshore teamwork.
- Participate and develop reports for the Weekly Status Reports, Monthly Status Reports, and Quarterly Status Reports.
- Participate in SCRUM and retrospectives.
- Develop, maintain, and enhance the build and release process.
- Manage security compliance of the Azure Subscription resources.
Qualifications
- 12+ years of experience as Full stack developer with at least 2-4 years in generative AI or RAG systems.
- Candidate must be in Pune location
- Immediate to 30 days joiners preferred
Required Skills
- Experience Programming APIs.
- Proficient in Python and C with hands-on experience building and consuming RESTful APIs.
- Strong experience with Microsoft Azure Cloud.
- Proven experience using generative AI frameworks for solution development and evaluation.
- Hands-on experience building AI agents with a solid understanding of agentic AI concepts.
- Deep expertise in Retrieval-Augmented Generation (RAG) patterns and LLM application design including prompting, orchestration tool usage, and grounding.
- Hands-on experience with Azure AI Services.
- Strong expertise in load testing, profiling, token optimization, caching strategies, autoscaling, GPU/CPU sizing, and telemetry.
- Skilled in designing, refining, and optimizing prompts for AI models and agents.
- Familiarity with multiple embedding generation techniques and selection strategies.
- Experience evaluating AI agent responses and continuously fine-tuning model and agent behavior.
- Experience with Power Automate and automation-driven enterprise solutions.
- Hands-on experience with Azure DevOps (ADO) for CI/CD and lifecycle management.
- Strong hands-on experience with AI SDKs and APIs for end-to-end solution development.
Preferred Skills
- Expertise Level: Expert in .NET, React, AI Solutions, Copilot Studio, Azure Foundry, Azure AI Services.
- Good Knowledge in Python, Azure services, Web App, App Insights, Kubernetes, Container Apps, Azure AI Search, SDLC Lifecycle.
- Expert in Partner Client Communications.
