About this role
Object Technology Solutions, Inc (OTSI) has an immediate opening for a Lead Agentic AI Engineer.
Lead Agentic AI Engineer (Hyderabad)
Experience: 10+ Years
MAJOR RESPONSIBILITIES
Technical Leadership & Architecture
- Lead the design, development, and optimization of enterprise-grade agentic AI workflows.
- Architect scalable, secure, and multi-tenant SaaS platforms on public cloud environments (AWS/Azure/GCP).
- Define best practices for LLM integration, agent orchestration, and AI application architecture.
- Drive technical strategy for AI-powered products and accelerators.
Hands-on AI Engineering
- Build and deploy agentic AI systems using frameworks such as LangGraph, AutoGen, CrewAI, Agno, or Semantic Kernel.
- Integrate Large Language Models (LLMs) using AWS Bedrock, Azure AI Foundry, Vertex AI, and other AI platforms.
- Implement Retrieval-Augmented Generation (RAG), function calling, structured extraction, and intelligent document processing solutions.
- Develop Model Context Protocol (MCP) servers and enterprise AI integrations.
- Design and implement human-in-the-loop workflows for AI decision-making systems.
- Build PII detection, anonymization, and de-anonymization pipelines.
Security, Governance & Compliance
- Establish LLM governance practices including cost optimization, rate limiting, monitoring, and audit trails.
- Implement AI guardrails against prompt injection, data leakage, and hallucination risks.
- Ensure compliance with security standards such as ISO 27001, SOC 2, PCI DSS, and enterprise security policies.
- Design secure AI solutions with appropriate access controls and data protection mechanisms.
Cloud & SaaS Engineering
- Develop cloud-native AI applications using AWS, Azure, or GCP services.
- Design scalable multi-tenant SaaS architectures.
- Work with containerization and orchestration technologies including Docker and Kubernetes.
- Implement CI/CD automation using GitHub Actions, Terraform, or similar DevOps tools.
Customer & Sales Enablement
- Participate in customer technical discovery sessions and solution discussions.
- Support sales teams with technical demonstrations, RFP/RFI responses, and AI solution proposals.
- Translate customer requirements and feedback into product enhancements.
Mentorship & Collaboration
- Mentor engineering teams on agentic AI architecture, LLM development practices, and AI engineering standards.
- Collaborate with product, engineering, and customer teams to deliver innovative AI solutions.
- Drive best practices in AI observability, tracing, reliability, and compliance.
SKILLS AND ABILITIES REQUIRED:
- Strong experience in software engineering with expertise in Python development.
- Hands-on experience building production-grade AI/ML and Generative AI applications.
- LangGraph
- AutoGen
- CrewAI
- Agno
- Semantic Kernel
Experience integrating LLM platforms:
- AWS Bedrock
- Azure AI Foundry
- Vertex AI
Strong understanding of:
- Retrieval-Augmented Generation (RAG)
- Prompt Engineering
- Function Calling
- Structured Data Extraction
- Intelligent Document Processing
Experience with vector databases:
- Pinecone
- Weaviate
- Qdrant
- pgvector
Hands-on experience developing MCP (Model Context Protocol) servers.
Experience with AI security, governance, and guardrail frameworks:
- NeMo Guardrails
- Guardrails AI
- PII detection and redaction
Strong understanding of cloud platforms:
- AWS (EKS, Lambda, S3, RDS)
- Azure / GCP
Experience designing and implementing multi-tenant SaaS platforms.
Knowledge of databases:
- SQL
- Object Storage
- Vector Databases
Tired of cold applications?
Sign up with Clera and we'll reach out the moment a role actually fits you โ no more spraying applications into the void.
Know someone who'd be great for this?