Artificial Intelligence Engineer

Role: AI/ML Engineer

Experience : 6+ years

Location : Bengaluru, Chennai and Hyderabad

Shift Timings : 1 PM to 10 PM IST

Notice Period : 0-15 Days

Primary Skills – Strong AI/ML Background , Experience in Gen-AI with exposure to AWS Bedrock & Bedrock Agents, Multi-agent Orchestration, Databricks and AI Governance

Please find below detailed JD

1. AI Governance & Risk

• Translate AI governance frameworks such as NIST AI RMF, ISO/IEC 42001, and EU AI Act requirements into practical engineering controls.
• Implement PII detection, masking, and redaction at AI gateway and application layers.
• Implement data classification, lineage, and policy enforcement for AI workloads.
• Design permission-aware RAG so users and agents can retrieve only authorized enterprise data.
• Establish agent risk tiers based on autonomy, data sensitivity, tool access, and business impact.
• Implement human-in-the-loop approval gates for high-risk or irreversible actions such as database writes, financial transactions, and external communications.
• Implement monitoring for guardrail violations, policy deviations, anomalous agent behavior, and unauthorized tool usage.
• Maintain an enterprise AI inventory covering models, agents, tools/MCP servers, workloads, and associated risks.
• Support production change management and governance for models, prompts, agents, tools, and AI workflows.

2. Agentic AI & ML Engineering

• Design and develop production-grade multi-agent and agentic AI systems using frameworks such as LangGraph, Strands, AutoGen, CrewAI, or equivalent.
• Define clear autonomy boundaries, tool permissions, escalation paths, and failure-handling mechanisms for AI agents.
• Build enterprise RAG pipelines with access-controlled retrieval and governance-aware data flows.
• Design and implement prompt management and version control, including approval and evaluation gates before production deployment.
• Integrate MCP (Model Context Protocol) servers and tools using appropriate trust boundaries and per-agent permissions.
• Develop automated evaluation pipelines for quality, safety, grounding, reliability, and agent behavior.
• Implement continuous monitoring for model, prompt, retrieval, and agent performance drift.

3. AWS Architecture & Platform Engineering

• Design and implement secure AI workloads using AWS Bedrock, IAM, Lambda, ECS/Fargate, and related AWS services.
• Implement authentication, authorization, secrets management, network controls, and least-privilege access for AI workloads.
• Leverage Bedrock Guardrails and AgentCore or equivalent AWS-native capabilities where appropriate.
• Design scalable architectures for enterprise agentic workloads with appropriate isolation and security boundaries.
• Work with Databricks or equivalent data platforms to integrate data classification, permissions, and lineage into AI applications.

4. AI Observability & Cost Governance

• Implement LLM and agent observability using platforms such as Langfuse, Arize, or equivalent.
• Build dashboards and monitoring for:
• Evaluate and implement AI gateway solutions such as LiteLLM, Kong AI Gateway, Portkey, or AWS-native controls.