Job Description
<p><p><b>We are Hiring :</b></p><p><p><b><br/></b></p>We are Hiring GenAI professional with proven production-grade project deployment experience with strong expertise in Agentic AI.</p><br/><p><b>About the Role :</b></p><p><p><b><br/></b></p>We are looking for a GenAI professional with strong experience in NLP, Computer Vision, and LLM-based agentic systems.</p><br/><p>In this role, you will design, build, fine-tune, and deploy production-grade LLM agents and multi-modal AI applications that solve real-world business challenges.</p><br/><p>You will play a key role in shaping agent design, orchestration, and observability, ensuring enterprise-grade scalability, robustness, and performance.</p><br/><p><b>Key Responsibilities :</b></p><br/><p><b>Model & Agent Design :</b></p><p><p><b><br/></b></p>- Conceptualize, design, and implement LLM-powered agents and NLP solutions tailored to business needs.<br/><br/></p><p>- Build multi-agent and multi-modal AI applications/frameworks, ensuring interactivity, latency optimization, failover, and usability.<br/><br/></p><p>- Apply advanced design principles for structured outputs, tool usage, speculative decoding, AST-Code RAG, streaming, and async/sync processing.</p><br/><p><b>Hands-on Coding & Development :</b></p><p><br/></p><p>- Write, test, and maintain clean, scalable, and efficient Python code for LLMs and AI agents.<br/><br/></p><p>- Implement fine-tuning, embeddings, and prompt engineering with a focus on cost, latency, </p><p>and accuracy.<br/><br/></p><p>- Integrate models with vector databases (Milvus, Qdrant, ChromaDB, CosmosDB, MongoDB).</p><br/><p><b>Performance & Monitoring :</b></p><p><br/></p><p>- Monitor and optimize LLM agents for latency, scalability, robustness, and explainability.<br/><br/></p><p>- Implement observability and guardrails strategies for enterprise-safe AI deployments.<br/><br/></p><p>- Handle model drift, token consumption optimization, and error recovery mechanisms.</p><br/><p><b>Research & Innovation :</b></p><p><br/></p><p>- Read, interpret, and implement AI/Agent research papers into practical production-ready solutions.<br/><br/></p><p>- Stay ahead of academic and industry trends in Agentic AI, multimodal AI, orchestration </p><p>frameworks, and evaluation methodologies.<br/><br/></p><p>- Experiment with new AI orchestration tools, evaluation frameworks, and observability platforms (Arize or & Issue Resolution :</b></p><p><br/></p><p>- Diagnose and resolve model inaccuracies, system integration issues, and performance bottlenecks.</p><p><br/></p><p>- Apply advanced debugging techniques to troubleshoot deployment errors, data inconsistencies, and unexpected agent Learning & Adaptability :</b></p><p><br/></p><p>- Quickly unlearn outdated practices and adapt to emerging GenAI and Agentic AI technologies.</p><p><br/></p>- Contribute to a culture of innovation by experimenting, prototyping, and scaling cutting-edge AI solutions.</p><br/><p><b>Required Skills & Experience :</b></p><p><br/></p><p>- 5 - 9 years total experience, with 4+ years in NLP, CV, and LLMs.</p><p><br/>- Strong expertise in GenAI, LLMs, RAG pipelines, embeddings, and vector databases.<br/><br/></p><p>- Proficiency in Python with strong debugging and system design skills.<br/><br/></p><p>- Hands-on experience with Agentic AI frameworks (LangChain Agents, AutoGen, CrewAI, </p><p>Temporal, DSPy).<br/><br/></p><p>- Proven record of production-grade AI deployments (not just POCs).<br/><br/></p><p>- Cloud experience : Azure (preferred), AWS, or GCP.<br/><br/></p><p>- Knowledge of AI orchestration, evaluation, guardrails, and observability tools (Arize, Weights & Biases, etc.</p><br/></p> (ref:hirist.tech)