Artificial Intelligence Engineer LLM

Job description

<p>AI Engineer (LLM Focus) <br/><br/><b>Job Description : </b><br/><br/><b>Position Overview : </b></p><p><br/></p><p>We are seeking a highly skilled and forward-thinking AI Engineer specialized in Large Language Models (LLMs) to design, develop, and deploy innovative AI-powered applications and intelligent agents.

The ideal candidate will possess deep expertise in LLM engineering, including advanced prompt engineering strategies, fine-tuning, evaluation methodologies, and the development of systems using frameworks like Lang chain/Lang Graph.

You will have a strong background in software engineering and a passion for pushing the boundaries of what's possible with generative AI, bringing solutions from ideation and research through to robust and scalable production deployment.

<br/><br/><b>Experience : </b> 5 to 7 years of overall software development experience, with at least 3+ years specifically focused on AI development, including significant hands-on experience with Large Language Models, agent development, and related technologies.<br/><br/>Location : Bengaluru [Hybrid]<br/><br/>Employment Type : Full-time / Permanent<br/><b><br/></b><b>Key Responsibilities : </b><br/><b><br/></b>- LLM Application & Agent Development : Design, build, and optimize sophisticated applications, intelligent AI agents, and systems powered by Large Language Models.<br/><br/>- Advanced Prompt Engineering & Optimization : Develop, test, iterate, and refine advanced prompt engineering techniques to elicit desired behaviours, ensure reliability, and maximize performance from LLMs for various complex tasks.<br/><br/>- LLM Fine-Tuning & Customization : Lead efforts in fine-tuning pre-trained LLMs on domain-specific datasets to enhance their capabilities and align them with specific business needs.<br/><br/>- LLM Evaluation & Benchmarking : Establish and implement rigorous evaluation frameworks, metrics, and processes to assess LLM performance, accuracy, fairness, safety, and robustness.

<br/><br/>- Framework Utilization (Langchain/ LangGraph) : Architect and develop complex LLM-driven workflows, chains, multi-agent systems, and graphs using frameworks like Langchain and LangGraph.

<br/><br/>- Cross-Functional Collaboration : Collaborate closely with Principal Architects (including those based internationally), data scientists, software engineers, and product teams to integrate LLM-based solutions into new and existing products and services.

<br/><br/>- Performance, Scalability & Cost Optimization : Optimize LLM inference speed, throughput, scalability, and cost-effectiveness for production environments.

<br/><br/>- Stay Current with LLM Advancements : Continuously research, evaluate, and experiment with the latest LLM architectures, open-source models, prompt engineering methodologies, agentic AI patterns, fine-tuning methods, and ethical AI considerations.

<br/><br/>- LLM Ops & Governance : Contribute to building and maintaining LLMOps infrastructure, including model versioning, monitoring, feedback loops, data management for fine-tuning, and governance for LLM deployments.

<br/><br/>- API & Service Development : Develop robust APIs and microservices to serve LLM-based applications and agents reliably and at scale.

<br/><br/>- Documentation & Knowledge Sharing : Create comprehensive technical documentation, share expertise on LLM and agent development best practices, and present findings to both technical and non-technical stakeholders.

<br/><br/><b>Required Qualifications : </b></p><p><br/></p><p>- Educational Background : Bachelor's or master's degree in computer science, Artificial Intelligence, Machine Learning, Computational Linguistics, or a closely related technical field.

<br/><br/>- Professional Experience : 5-7 years of progressive experience in software development, with a minimum of 3+ years dedicated to AI development, including substantial hands-on experience in designing, building, and deploying LLM-based systems and AI agents.

<br/><br/>- Programming Proficiency : Expert proficiency in Python and its ecosystem relevant to AI and LLMs. <br/><br/>- LLM, NLP & Agent Expertise : Deep understanding of Natural Language Processing (NLP) concepts, Transformer architectures, the inner workings of Large Language Models, and principles of AI agent design.

<br/><br/>- LLM Frameworks & Tools : Significant hands-on experience with LLM-specific libraries and frameworks such as Hugging Face Transformers, Langchain, LangGraph, LlamaIndex, and similar tools for building LLM applications and agents.

<br/><br/>- Cloud Platform Experience : Solid experience with one or more major cloud platforms (AWS, GCP, Azure) and their respective AI/ML services, particularly those for deploying and managing LLMs (e.g., Amazon Bedrock, Google Vertex AI, Azure OpenAI Service).

<br/><br/>- Fine-Tuning & Evaluation Experience : Demonstrable experience in fine-tuning LLMs and implementing robust evaluation strategies for both models and agent performance.

<br/><br/>- MLOps/LLMOps Practices : Experience with MLOps principles and tools, adapted for the LLM lifecycle (e.g., experiment tracking, model registries, CI/CD for LLMs and agent-based systems).

<br/><br/>- Data Handling for LLMs : Understanding of data preprocessing, augmentation, and management techniques for training and fine-tuning LLMs. <br/><br/>- Version Control : Proficiency with Git and collaborative development workflows.

<br/><br/><b>Preferred Qualifications :</b><br/><br/>- Advanced LLM Architectures & Prompt Engineering : Deep experience with various LLM architectures, their trade-offs, and mastery of advanced prompt engineering techniques.

<br/><br/>- Autonomous Agent & Multi-Agent Systems : Proven experience in designing, developing, and deploying autonomous AI agents or complex multi-agent systems.

<br/><br/>- Vector Databases : Familiarity with vector databases (e.g., Pinecone, Weaviate, Milvus, Chroma) for retrieval augmented generation (RAG) and semantic search in agentic architectures.

<br/><br/>- Distributed Systems for LLMs : Knowledge of distributed training and inference techniques for very large models.

<br/><br/>- Ethical AI & Responsible LLM/Agent Development : Strong understanding of ethical considerations, bias detection, and responsible AI practices in the context of LLMs and AI agents.

<br/><br/>- Research & Publications : Contributions to LLM or AI agent research, publications in relevant conferences/journals, or active participation in open-source LLM/agent projects.

<br/><br/>- Domain-Specific LLM/Agent Applications : Experience applying LLMs and agents to solve problems in specific industry domains.

<br/><br/>- Cloud Certifications : Relevant cloud certifications (e.g., AWS Certified Machine Learning, Google Professional Machine Learning Engineer, Microsoft Certified : Azure AI Engineer Associate or similar MCP credentials).

<br/><br/><b>Technical Skill set Summary : </b></p><p><p><b><br/></b></p><p><b>- Programming : Python (expert), SQL.

</b></p><br/>- LLM/NLP/Agent Frameworks : Hugging Face Transformers, Langchain, LangGraph, LlamaIndex, PyTorch, TensorFlow, frameworks for agent development.

<br/><br/>- Cloud Platforms & LLM Services : AWS (SageMaker, Bedrock), GCP (Vertex AI), Azure (Machine Learning, Azure OpenAI Service).

<br/><br/>- Tools : Docker, Kubernetes, MLflow, Weights & Biases, Vector Databases (e.g., Pinecone, Weaviate).

<br/><br/>- Databases : Relational (SQL Server, PostgreSQL, MySQL), NoSQL (MongoDB), and Vector Databases.

<br/><br/><b>Soft Skills :</b><br/><br/>- Exceptional analytical, creative, and critical thinking skills with a talent for innovative problem-solving in the generative AI and intelligent agent space.

<br/><br/>- Outstanding communication skills, with the ability to explain complex LLM concepts and agent system designs to diverse audiences.

<br/><br/>- Proven ability to work effectively both independently and as a key contributor in collaborative, agile teams.

<br/><br/>- Meticulous attention to detail, especially regarding data quality, model behavior, agent reliability, and system robustness.

<br/><br/>- A proactive, highly adaptable mindset with an insatiable curiosity and passion for the rapidly evolving field of Large Language Models and AI agents.

</p> (ref:hirist.tech)

Required Skill Profession

Computer Occupations