| Job Description: |
Role Overview
We are seeking a Senior AI Engineer with deep, hands on expertise in Generative AI, multi agent orchestration, and LLM based systems to design, build, and scale secure, production grade AI platforms. The role requires strong engineering rigor, practical experience beyond PoCs, and the ability to operationalize agentic AI in complex enterprise environments.
________________________________________
Core Skills & Responsibilities
Generative AI & LLM Engineering
• Strong hands on experience building LLM powered applications for reasoning, summarization, Q&A, and content generation
• Expertise in prompt engineering, prompt optimization, and systematic prompt evaluation
• Ability to generate structured and deterministic outputs for downstream consumption
• Apply grounding, response validation, and hallucination mitigation techniques
________________________________________
Multi Agent Orchestration & LangGraph (Must Have)
• Strong hands on experience designing and implementing multi agent AI systems
• Practical experience working with agent orchestration frameworks, specifically LangGraph
• Design and implement:
o Orchestrator / supervisor agent patterns
o Intent routing, task decomposition, and agent sequencing
o Dependency management and agent handoffs
• Implement tool calling patterns, shared context management, and output aggregation across agents
• Experience managing agent state, memory, and execution flow in production environments
________________________________________
Retrieval Augmented Generation (RAG)
• Build and optimize RAG pipelines across large unstructured datasets
• Hands on experience with:
o Embedding strategies
o Vector databases and semantic search
o Chunking, ranking, and metadata based retrieval
• Ensure responses are traceable, explainable, and source grounded
________________________________________
AI Application Engineering
• Strong backend engineering skills using Python
• Design modular, API first AI services using scalable architectures
• Integrate AI services with external systems and tools via secure APIs
• Efficient handling of long running agent workflows and asynchronous execution
________________________________________
Cloud Native AI & Platform Skills
• Experience deploying AI solutions on cloud native platforms
• Familiarity with:
o Containerized AI workloads
o CI/CD pipelines for AI and agent services
o Scalable, fault tolerant system design
• Experience managing structured and unstructured data storage for AI workloads
________________________________________
AI Governance, Security & Reliability
• Implement guardrails and safety controls, including:
o Prompt injection prevention
o Access control and role based execution
o Output validation and policy enforcement
• Support observability for:
o Agent behavior and execution flow
o Confidence scoring and failure detection
o Usage patterns and anomaly detection
• Design AI systems that are auditable, explainable, and enterprise ready
________________________________________
Collaboration & Technical Leadership
• Provide technical leadership across AI and GenAI initiatives
• Review AI designs, orchestration flows, and implementation quality
• Mentor junior AI engineers on agent design and best practices
• Collaborate with architects, data scientists, and platform engineers
________________________________________
Required Qualifications
• Strong experience as a Senior AI / GenAI Engineer
• Proven, hands on experience with multi agent orchestration using LangGraph
• Advanced knowledge of:
o LLMs and agentic AI systems
o RAG architectures
o Python based AI development
• Experience delivering production grade AI systems, not just experiments
________________________________________
Preferred Qualifications
• Experience designing large scale agent based platforms
• Exposure to LLMOps / MLOps practices
• Familiarity with model and agent evaluation techniques
• Experience working in regulated or security sensitive environments
________________________________________
Key Expectations
• Deliver scalable, reliable, and well orchestrated AI systems
• Demonstrate deep hands on ownership of multi agent execution logic
• Balance innovation with robustness, security, and maintainability
|
