AI applications engineer (CE712SF RM 3625)

Position: AI applications engineer (CE712SF RM 3625)

Shift timing : IST (with MT overlap)
Work Mode : Work from Office
Relevant Experience required : 6 – 10 Years
Education Required : Bachelor’s / Masters / PhD: Bachelor’s

Mandatory skills: Generative AI & LLMs, Python & ML Libraries, RAG & Vector Databases, Agentic AI Workflows, Cloud Platforms (Azure, AWS, GCP), Fine-tuning & Parameter-efficient Tuning, Orchestration Libraries (e.g., LangGraph, Crew AI)

Good to have skills: Multimodal Models & Retrieval, CI/CD for AI pipelines, containerization (Docker), and cloud AI services (Azure ML, AWS Sagemaker, GCP Vertex), APIs, Microservices, & Containerization, Data Governance & Security

Overview
We are seeking an experienced AI Applications Engineer to architect, implement, and optimize advanced AI solutions, with a particular focus on Large Language Models (LLMs), agentic pipelines, workflow automation, and generative AI. You will work on high-impact initiatives across engineering automation, smart knowledge retrieval, and autonomous agentdriven workflows using the latest in AI research and toolkits.

Core Responsibilities
o Design and build advanced AI-driven systems utilizing LLMs (e.g., Azure OpenAI GPT Models, Claude, Llama, Mistral, Gemini, and open-source models) for tasks such as text understanding, generation, summarization, and contextual reasoning within engineering workflows.
o Architect and deploy agentic pipelines (multi-agent systems, autonomous LLM agents, chain-of-thought/reasoning systems) for process automation, decision support, and engineering knowledge orchestration.
o Develop and implement Advanced Retrieval-Augmented Generation (RAG) solutions — combining LLMs with vector databases, search engines, and enterprise knowledge sources for high-fidelity document analysis and Q&A.
o End-to-End automation of complex human-in-the-loop processes by chaining LLMs, expert systems, and external tools using orchestration frameworks (such as LangChain, LlamaIndex, Haystack, CrewAI, etc.).
o Evaluate, select, and integrate modern and emerging AI tools, APIs, and infrastructure (LLMOps, vector stores, document loaders, prompt management, agents frameworks, etc).
o Fine-tune, deploy, and monitor LLMs on private/in-house datasets to solve unique domain challenges and maintain compliance/privacy.
o Stay current with the fast-evolving AI landscape (open weights, small/efficient models, guardrails, synthetic data, evaluation techniques, multimodal models, etc.), and bring new approaches into the organization.

Essential Qualifications
o Bachelor’s/Master’s/PhD in Computer Science, Artificial Intelligence, or related field.
o Deep expertise in building with LLMs (commercial and open-source): prompt engineering, model selection, fine-tuning, and evaluation.
o Hands-on experience developing agentic pipelines and workflow automations using frameworks like LangChain, LlamaIndex, Semantic Kernel, Haystack, and orchestration ofcloud/on-prem LLM endpoints.
o Proven track record designing RAG systems (vector database management, chunking strategies, search optimization, retrieval pipelines—using Pinecone, Weaviate, FAISS, ChromaDB, Elastic, etc.).
o Working knowledge of multi-modal AI (text/audio/image/diagram/video handling), Graphbased retrieval knowledge graphs, and semantic search.
o Strong Python skills, deep experience with modern AI/ML/NLP libraries (Transformers, Pydantic, FastAPI, HuggingFace, Azure OpenAI, etc.).
o Experience integrating AI solutions into real-world engineering or enterprise applications (APIs, plugins, workflow tools, agent frameworks, MLOps/LLMOps).
o Familiarity with advanced prompting, guardrails/AI safety, evaluation and monitoring of AI systems, and leveraging synthetic data

Preferred/Bonus:
o Experience optimizing for model cost, latency, reliability, and scaling in production.
o Understanding of privacy, security, and compliance in LLM/AI applications (PII scrubbers, access controls, audit trails).
o Experience orchestrating multi-agent/agentic workflows (CrewAI, AutoGen, OpenAgents, etc.).
o Familiarity with CI/CD for AI pipelines, containerization (Docker), and cloud AI services (Azure ML, AWS Sagemaker, GCP Vertex).

General:
o Strong critical thinking and research skills, enthusiastic about rapid learning and experimenting with new AI capabilities.
o Excellent communication and documentation abilities.
o Ability to work in fast-moving, highly collaborative environments with evolving requirements

*******************************************************************************************************************************************