Job Description

Roles & Responsibilities

LLM Solution Design & Development

• Architect and deliver production-ready LLM applications, including conversational agents, intelligent assistants, and RAG pipelines with advanced retrieval and re-ranking.
• Build multi-agent systems using Lang Chain, Lang Graph, Auto Gen, or Crew AI; apply prompt engineering techniques to optimize model performance.
• Integrate LLM solutions with enterprise systems via REST APIs and event-driven architectures.

Model Fine-Tuning & Optimization

• Lead fine-tuning (LoRA, QLoRA, instruction tuning) and benchmark foundation models such as Open AI, Mistral, Llama, and Gemini for specific use cases.
• Optimize for latency, cost, and throughput; design evaluation frameworks to measure accuracy, hallucination, and safety.

Agentic AI & Workflow Automation

• Design agentic workflows with tool use, memory management, planning loops, and human-in-the-loop controls.
• Build AI-driven automation pipelines across structured and unstructured enterprise data sources.

Vector Databases & Knowledge Infrastructure

• Design and manage vector stores (Pinecone, Weaviate, Qdrant, FAISS, or PG Vector) with semantic and hybrid search strategies.
• Maintain knowledge bases powering enterprise AI applications, ensuring accuracy and freshness of indexed content.

Technical Leadership & Mentoring

• Guide and review the work of associate-level engineers; contribute to reusable frameworks and internal engineering standards.
• Lead client workshops, technical discovery sessions, and proof-of-concept demonstrations; produce clear solution design documentation.

Trend Monitoring & Innovation

• Evaluate emerging LLMs, multimodal models, and local inference runtimes; prototype new tools and share findings with the team.
• Contribute to Beinex thought leadership through internal knowledge-sharing sessions, technical write-ups, or industry presentations.

Desired Candidate Profile

• 5+ years of professional experience in AI Engineering, Machine Learning, or Applied NLP, with at least 2 years focused on LLMs and Generative AI.
• Strong proficiency in Python and experience with Hugging Face Transformer Library, Lang Chain, Lang Graph, Fast API, and PyTorch.
• Deep practical knowledge of LLM fine-tuning, prompt engineering, RAG pipeline design, and agentic AI development.
• Hands-on experience with vector databases such as Pinecone, Weaviate, Qdrant, FAISS, or PG Vector, along with embedding models.
• Proven ability to deploy and productionize AI solutions in AWS, Azure, or GCP using Docker and Kubernetes.
• Experience integrating AI solutions with enterprise platforms through REST APIs, webhooks, or event-driven architectures.
• Strong understanding of responsible AI principles, including hallucination mitigation, output evaluation, content safety, and model governance.
• Excellent communication skills with the ability to explain complex technical concepts to both technical and business stakeholders.
• Demonstrated ability to independently lead AI projects from solution design through production deployment.

Preferred Certifications

• AWS Certified Machine Learning – Specialty, Azure AI Engineer, GCP Professional Machine Learning Engineer, or equivalent cloud AI/ML certification.
• Deep Learning Specialization.
• LLM Engineering or Generative AI certifications from recognized learning platforms such as Hugging Face, DeepLearning AI, or Databricks.
• Certified Kubernetes Application Developer (CKAD) is an added advantage.

Company Industry

• IT - Software Services

Department / Functional Area

• Engineering
•