Job Summary
R Systems is looking for a highly skilled Gen AI Lead Engineer to design, develop, and deploy production-grade Generative AI applications.
The ideal candidate should have strong experience in Python, LLM-based application development, Retrieval-Augmented Generation (RAG), Agentic AI, and modern AI engineering practices.
This role requires a hands-on technical leader who can architect scalable AI solutions, mentor engineering teams, and drive innovation across enterprise AI initiatives.
Key Responsibility Areas
Generative AI Solution Development :
- Design, develop, and deploy enterprise-grade Generative AI applications using Large Language Models (LLMs).
- Build scalable AI-powered solutions involving prompt engineering, structured outputs, context management, and token optimization.
- Develop intelligent AI assistants, copilots, knowledge search, and workflow automation solutions aligned with business requirements.
- Continuously evaluate and enhance AI models to improve response quality, performance, and Generation (RAG) & Agentic AI :
- Design and implement advanced RAG pipelines using semantic and hybrid search techniques, chunking strategies, vector databases, query rewriting, re-ranking, and grounding mechanisms.
- Build and optimize autonomous AI agents capable of planning, tool execution, memory management, and multi-agent orchestration.
- Develop secure and reliable agent workflows with robust error handling, retry mechanisms, and tool integrations using MCP or equivalent standards.
AI Engineering & LLMOps
- Establish best practices for prompt lifecycle management, model evaluation, regression testing, tracing, observability, and production monitoring.
- Build evaluation frameworks using automated testing techniques, including LLM-as-a-Judge methodologies, while implementing safeguards against hallucinations and model drift.
- Ensure AI applications are production-ready by monitoring performance, latency, quality, and operational costs.
Application Development & Cloud Deployment
- Develop backend services and APIs using Python and FastAPI, ensuring scalable, secure, and high-performance application architecture.
- Build cloud-native AI applications leveraging platforms such as AWS Bedrock, Azure AI Foundry, or Google Vertex AI.
- Deploy applications using Docker, Kubernetes, and serverless architectures while supporting CI/CD pipelines and DevOps best practices.
Data Engineering & AI Infrastructure
- Design and manage AI data pipelines using tools such as Pandas, Airflow, Databricks, or equivalent workflow orchestration platforms.
- Work with relational databases, vector databases, and semantic search platforms including FAISS, Pinecone, Weaviate, pgvector, Azure AI Search, or OpenSearch to enable efficient retrieval and knowledge management.
Technical Leadership
- Lead a team of AI engineers by providing technical guidance, conducting code reviews, and mentoring team members on modern AI engineering practices.
- Drive architecture discussions, technology selection, and engineering best practices for scalable AI solutions.
- Collaborate closely with product managers, architects, and cross-functional teams to translate business requirements into innovative AI-powered solutions.
AI Governance & Security
- Implement AI security best practices by addressing prompt injection, jailbreak attacks, data leakage risks, hallucination mitigation, and validation mechanisms.
- Ensure responsible AI development by incorporating guardrails, governance frameworks, and model safety standards throughout the solution lifecycle.
Required Skills & Qualifications
- The ideal candidate should possess 6+ years of overall software engineering experience, including 2+ years of hands-on experience developing and deploying LLM-based applications in production environments.
- Strong expertise in Python and FastAPI is essential, along with practical experience in prompt engineering, Retrieval-Augmented Generation (RAG), agentic AI systems, LLMOps, and AI observability.
- Candidates should have a solid understanding of software engineering principles, REST API development, SQL, data modelling, CI/CD, and version control.
- Hands-on experience with AI orchestration frameworks such as LangChain, LangGraph, LlamaIndex, or Semantic Kernel, vector databases including Pinecone, FAISS, Weaviate, pgvector, or Azure AI Search, and cloud AI platforms such as AWS Bedrock, Azure AI Foundry, or Google Vertex AI is expected.
- Familiarity with Docker, Kubernetes, Airflow, Databricks, and AI-assisted development tools like Cursor, GitHub Copilot, or Claude Code will be an added advantage.
- A Bachelor's degree in Computer Science, Information Technology, Engineering, MCA, M.Tech, or an equivalent qualification is required.
(ref:hirist.tech)
