| IC | AI Engineer | Bengaluru
Share
Job Location:
Monthly Salary:
Posted on:
18 hours ago
Vacancies:
1 Vacancy
Job Summary
Total Exp : 5 Years
JD :
Conversational AI Ownership: Lead the architecture development and optimization of Intelligent Document Processing intelligent chatbots and conversational agents including RAG pipelines tool/function calling memory and multi agent workflows (e.g. LangChain/LangGraph/Hugging Face).
Application & Platform Engineering: Build production grade microservices/APIs (FastAPI/Flask); integrate with enterprise systems (CRM claims knowledge bases) and manage channel integrations (web mobile contact center).
Cloud Native Deployments: Deploy to Azure GCP (Container Apps/Functions/Cloud Run); manage secrets (Key Vault/KMS) configuration autoscaling and reliability.
CI/CD & Release Practices: Establish automated tests canary/blue green deployments rollback strategies and artifact versioning (models/prompts/flows) with MLflow/Azure ML.
Model Development & Deployment: Build test deliver and maintain robust AI systems and services that solve complex business challenges-spanning LLM applications retrieval and inference APIs.
Business Alignment: Influence and translate strategic business objectives into actionable technical requirements system design and success metrics.
Health Pillar Support: Drive ideation and delivery of AI solutions within the health vertical-especially AI based conversational chatbots and agentic assistants.
Responsible AI Leadership: Embed the highest standards of AI ethics and Responsible AI in all phases of solution design deployment and operations.
Collaboration & Cross Functional Delivery: Partner closely with Data Science Engineering Product UX Risk/Compliance and Operations to plan ship and iterate LLM systems; coordinate with channel teams; co create runbooks and ensure smooth handoffs to operations.
Innovation & Thought Leadership: Continuously explore and implement best in class solutions in Generative and Agentic AI platform components and reusable accelerators.
Security & Responsible AI Guardrails: Enforce PII redaction content moderation red teaming policy compliance and audits aligned to enterprise governance and APAC regulations.
Performance & UX: Tune for low latency high reliability and high quality conversational UX including handoffs feedback loops and continuous evaluations.
Mandatory: Python SQL LangChain/LangGraph FastAPI/Flask Any cloud LLM
Application & Platform Engineering: Build production grade microservices/APIs (FastAPI/Flask); integrate with enterprise systems (CRM claims knowledge bases) and manage channel integrations (web mobile contact center).
Cloud Native Deployments: Deploy to Azure GCP (Container Apps/Functions/Cloud Run); manage secrets (Key Vault/KMS) configuration autoscaling and reliability.
CI/CD & Release Practices: Establish automated tests canary/blue green deployments rollback strategies and artifact versioning (models/prompts/flows) with MLflow/Azure ML.
Model Development & Deployment: Build test deliver and maintain robust AI systems and services that solve complex business challenges-spanning LLM applications retrieval and inference APIs.
Business Alignment: Influence and translate strategic business objectives into actionable technical requirements system design and success metrics.
Health Pillar Support: Drive ideation and delivery of AI solutions within the health vertical-especially AI based conversational chatbots and agentic assistants.
Responsible AI Leadership: Embed the highest standards of AI ethics and Responsible AI in all phases of solution design deployment and operations.
Collaboration & Cross Functional Delivery: Partner closely with Data Science Engineering Product UX Risk/Compliance and Operations to plan ship and iterate LLM systems; coordinate with channel teams; co create runbooks and ensure smooth handoffs to operations.
Innovation & Thought Leadership: Continuously explore and implement best in class solutions in Generative and Agentic AI platform components and reusable accelerators.
Security & Responsible AI Guardrails: Enforce PII redaction content moderation red teaming policy compliance and audits aligned to enterprise governance and APAC regulations.
Performance & UX: Tune for low latency high reliability and high quality conversational UX including handoffs feedback loops and continuous evaluations.
Mandatory: Python SQL LangChain/LangGraph FastAPI/Flask Any cloud LLM
Key Skills
- ASP.NET
- Health Education
- Fashion Designing
- Fiber
- Investigation
