Roles and Responsibilities

• Develop, optimize, and deploy RAG-based LLM solutions to meet business requirements.
• Fine-tune and implement prompt engineering for LLMs, improving performance and accuracy.
• Design and integrate information retrieval pipelines, leveraging vector databases and embedding techniques.
• Work with AWS and AWS Bedrock LLM suite for scalable AI model deployment.
• Collaborate with cross-functional teams to align AI solutions with business goals.
• Utilize agent-based prompting techniques (e.g., LangChain) for enhancing model output.
• Apply DevOps practices (CI/CD, Docker, Kubernetes) for smooth deployment and management.
• Communicate complex technical concepts to both technical and non-technical stakeholders.

Required Skills & Experience

• 3+ years in Python, ML, and AI development.
• Experience with AWS, including Bedrock LLM suite and cloud-based AI solutions.
• 1+ year in NLP, LLMs, and RAG models.
• Proficiency with TensorFlow, PyTorch, and Hugging Face Transformers.
• Strong background in vector databases, embedding techniques, and agent-based prompting.
• Familiarity with DevOps practices (CI/CD, Docker, Kubernetes).
• Excellent problem-solving and communication skills.

Preferred Skills

• Experience with AI orchestration tools (e.g., ArgoCD).
• Ability to design and explain data flow diagrams and solution architectures.
• Familiarity with LLM UI/Frontend design and deployment.

Posted By