AI Engineer

Position Name - AI Engineer

Responsibilities

• Design, build, and deploy production-grade LLM solutions, RAG pipelines, and agentic AI systems on cloud platforms (primarily Azure).
• Conduct AI readiness workshops, map business processes, and define automation ROI through intelligent AI solutions.
• Architect and implement multi-agent workflows using frameworks such as LangChain, LangGraph, CrewAI, and AutoGen.
• Integrate AI solutions with enterprise systems (ServiceNow, Jira, CRMs, ERPs) via REST APIs and webhooks.
• Apply advanced LLM techniques including prompt engineering, Retrieval-Augmented Generation (RAG), LLM fine-tuning, and tool/function calling with secure, scalable design.
• Monitor performance, drive adoption, and iterate based on telemetry, evaluation pipelines, and user feedback.

Client Discovery & Solutioning

• Run AI readiness workshops, map current processes, and quantify automation ROI.
• Translate business requirements into technical agent designs and LLM-based solution architectures.
• Conduct client demos, manage technical Q&A, and communicate AI solutions clearly to both technical and non-technical stakeholders.

Agent & Automation Development

• Build conversational and task-oriented AI agents using low/no-code and Python-native agentic frameworks (LangChain, LangGraph, CrewAI, AutoGen, LlamaIndex).
• Design and implement RAG pipelines with vector stores (ChromaDB, FAISS, Pinecone, Qdrant, OpenSearch) and semantic search over enterprise data.
• Integrate AI solutions with enterprise applications (M365, Jira, ServiceNow, CRMs, ERPs) via APIs and webhooks.
• Implement Model Context Protocol (MCP) servers and clients for standardised, tool-based agentic workflows.
• Apply data-governance guardrails, prompt engineering best practices, and observability/logging across all deployments.

MLOps & Continuous Improvement

• Configure evaluation pipelines, drift monitoring, and automated performance-improvement triggers.
• Analyse usage telemetry and user feedback; iterate agent designs to maximise adoption and business impact.
• Lead fine-tuning efforts on models such as GPT-4o, Gemini, and open-source LLMs (Llama) to improve intent recognition and output quality.

Security & Compliance

• Perform threat modelling and apply security guardrails to LLM pipelines (prompt injection defence, data privacy, GxP or equivalent compliance where applicable).
• Collaborate with cybersecurity stakeholders on secure AI architecture design and deployment practices.

Thought Leadership & Enablement

• Document reusable patterns, RAG architectures, prompt templates, and agentic playbooks.
• Mentor junior engineers on prompt engineering, Python development, and LLM best practices.
• Present at client webinars, internal peer groups, and industry events.

Skills, Knowledge, and Experience

• 4-6 years of hands-on experience building and deploying production-grade Generative AI / LLM solutions.
• Strong proficiency in Python for AI development, API integration, and backend services (FastAPI, RESTful APIs).
• Hands-on experience with LLM orchestration frameworks: LangChain, LangGraph, AutoGen, CrewAI, or LlamaIndex.
• Proven experience designing and deploying RAG pipelines with vector stores (ChromaDB, FAISS, Pinecone, Qdrant, or similar).
• Solid understanding of Azure AI services: Azure OpenAI Service, Azure AI Search, Azure AI Services, Azure Data Factory.
• Experience integrating AI systems with enterprise tools (Jira, ServiceNow, CRMs, ERPs) via REST APIs and webhooks.
• Strong understanding of LLM security guardrails, prompt injection risks, and data governance.
• Excellent English communication skills; ability to engage clients, run workshops, and present technical concepts clearly.
• 4+ hour overlap with U.S. Eastern Time (for remote India-based roles).

Preferred Skills and Qualifications

• Hands-on experience with multi-agent systems and Model Context Protocol (MCP).
• Experience with Python Programming and LLM fine-tuning on models such as GPT-4o, Gemini, or open-source Llama variants.
• Familiarity with containerisation and deployment tools: Docker, Git, CI/CD pipelines.
• Experience with graph databases (Neo4j) or knowledge graphbased AI architectures.
• Past AI deployments in domains such as IT operations, pharma, QA/testing, Sales, HR, or Finance.
• Certifications: Microsoft AI-102 (Azure AI Engineer Associate), Microsoft DP-100 (Azure Data Scientist), or Google Cloud Professional ML Engineer.

Industry

Information Technology / Managed Services

Employment Type

Full-Time

Benefit

Industry-leading Compensation + HR Benefits.