Skills: Python;Azure;LLMs;Gen AI;Agentic AI;LangChain;LangGraph;Semantic Kernel;MS Auto Gen
Experience in Years: 10
Type: Full Time
Sr. AI Engineer – Generative AI & Agentic AI
- We are looking for an experienced AI Engineer responsible for designing, developing, and deploying Generative
- AI and Agentic AI solutions that support enterprise-scale business use cases. The role will build intelligent
- systems that integrate complex backend services and client-facing applications across web, mobile and
- The primary responsibility is to design and develop AI-powered applications, autonomous agents and multi-agent
- workflows while coordinating with cross-functional teams across architecture, engineering, product and business
- functions. A commitment to collaborative problem solving, sophisticated design and product quality is essential.
- This role requires strong hands-on engineering experience, practical working knowledge of modern agent
- frameworks, and the ability to deliver secure, scalable, observable and governed AI solutions in cloud-native
- Design and build enterprise-grade Generative AI applications using Large Language Models (LLMs) across business and technology use cases.
- Develop Agentic AI solutions including autonomous agents, multi-agent orchestration, tool-driven workflows and decision support systems.
- Implement robust Retrieval-Augmented Generation (RAG) architectures using embeddings, vector databases, semantic search and optimized retrieval strategies.
- Integrate AI services with enterprise APIs, middleware, backend systems and client channels such as web and mobile applications.
- Apply prompt engineering, tool/function calling, memory management, context engineering and agent orchestration patterns to improve quality, latency and cost efficiency.
- Deploy scalable AI workloads on Azure and AWS cloud platforms using modern DevOps, CI/CD, container and Kubernetes practices.
- Establish model evaluation, guardrails, observability, security controls and AI governance practices aligned to enterprise standards.
- Collaborate with product owners, enterprise architects, engineering teams and business stakeholders to convert business needs into secure, reusable and sustainable AI capabilities.
- Discover technical debt and continuous improvement opportunities in existing systems and influence the technical backlog with architecture and product stakeholders.
- Mentor engineers, promote engineering craftsmanship, and support communities of practice for AI engineering, cloud-native development and automation.
3. JOB CONTEXT
Specific Accountability
- Build production-grade AI agents using LangChain, LangGraph, Microsoft Semantic Kernel and Microsoft AutoGen; working experience with Semantic Kernel and AutoGen is mandatory.
- Design and implement multi-agent workflows covering planning, tool use, state management, memory, feedback loops, human-in-the-loop controls and workflow-driven decisions.
- Architect end-to-end data indexing pipelines optimized for semantic search, RAG quality, retrieval latency and answer relevancy.
- Design resilient data ingestion frameworks that ensure high availability and low latency for vectorized datasets.
- Implement context engineering strategies to reduce token utilization, manage prompt/context windows and improve end-to-end inference latency.
- Evaluate and improve AI agent performance using relevant metrics including response quality, grounding, retrieval precision/recall, faithfulness, latency, cost, safety and task completion.
- Deploy and manage models using Azure OpenAI Service, Amazon Bedrock and Google Vertex AI where required by solution constraints.
- Integrate pre-built AI APIs for speech-to-text, computer vision and natural language processing where they add business value.
- Leverage serverless architectures such as AWS Lambda and Azure Functions to trigger AI inference, data pre-processing and asynchronous workflow steps.
- Implement CI/CD pipelines with code quality checks, static code analysis, security scanning, requirement traceability and Jira integration.
- Operate monitoring, logging and alerting for AI, application and cloud environments with measurable reliability and supportability.
- Ensure SDLC, security, data protection, compliance and architecture governance procedures are followed for AI-powered services.
- Practical experience with responsible AI controls, AI red-teaming, policy-based guardrails and enterprise AI governance.
Added Advantage Working experience in building agents using Microsoft Agent Framework or equivalent Microsoft-native agent development capabilities.
4. QUALIFICATIONS & EXPERIENCE:
- Bachelor’s degree in Computer Science, Software Engineering, Information Technology, Data Science, Artificial Intelligence or a related discipline.
- Relevant cloud, AI engineering, machine learning or architecture certifications are preferred.
- Senior professional with around 10 years of total software engineering, architecture, cloud or platform.
- Minimum 3+ years of relevant hands-on AI Engineering experience, including Generative AI and practical LLM-based application delivery.
- Strong proficiency in Python, including NumPy, pandas, FastAPI and hands-on experience with PyTorch or TensorFlow.
- Hands-on experience with LangChain and LangGraph; mandatory working experience with Microsoft Semantic Kernel and Microsoft AutoGen.
- Experience implementing RAG using embeddings, vector databases, semantic search, retrieval optimization and model evaluation techniques.
- Experience deploying and managing models using Amazon Bedrock, Azure OpenAI Service and Google.
- Hands-on experience with microservices, containers, APIs, event-driven architecture, cloud-native services and evolutionary architecture practices.
- Experience managing and deploying AI workloads on Kubernetes in cloud-native and/or hybrid.
- Experience with CI/CD tools such as Jenkins or GitLab, DevOps toolchains, configuration management and cloud/on-prem deployment pipelines.
- Experience setting up pipelines with static code analysis, requirement tagging in Jira, quality gates and release governance.
- Experience operating monitoring tools for traditional infrastructure, cloud environments and AI-enabled business applications.
- Strong hands-on problem-solving mindset with the ability to analyze trade-offs and deliver sustainable, secure and high-quality solutions.
Key Technical Skills
- Generative AI, Agentic AI, autonomous agents, multi-agent orchestration and workflow-based AI systems.
- LLMs, embeddings, vector databases, RAG, semantic search, model evaluation, guardrails, observability and AI governance.
- Semantic Kernel, AutoGen, LangChain, LangGraph and similar agent frameworks.
- Python, FastAPI, PyTorch/TensorFlow, REST APIs, microservices, serverless functions and event-driven integration.
- Azure, AWS, Kubernetes, containers, CI/CD, DevOps automation, monitoring and secure software delivery.
Behavioural / Leadership Skills
- Strong collaborative mindset for agile architecture and decentralized decision making.
- Proactive, positive and growth-oriented leadership style with the ability to motivate engineers and foster craftsmanship.
- Strong communication, stakeholder engagement and influencing skills across product, business, architecture and engineering teams.
- Analytical, system-thinking and pragmatic problem-solving approach with commitment to product quality.
ANNEXURE: TECHNICAL & BEHAVIOURAL COMPETENCIES
- Agentic AI engineering using Semantic Kernel, AutoGen, LangChain, LangGraph and related frameworks.
- RAG architecture, embeddings, vector database design, semantic search and retrieval optimization.
- Cloud-native deployment, Kubernetes operations, CI/CD automation and observability for AI workloads.
- Responsible AI, model evaluation, guardrails, governance, security and operational resilience.
- Collaboration, ownership, engineering craftsmanship and continuous improvement.
- Stakeholder management, clear communication, mentoring and cross-functional leadership.
- Analytical thinking, pragmatic decision making, curiosity and growth mindset.