Description

You will design, develop, and deploy scalable machine learning and AI-driven solutions, with a strong focus on production-grade systems and Large Language Models.

This role is remote.

Responsibilities

• Architect and build production ML systems, including model serving, evaluation, monitoring, and data pipelines.
• Develop autonomous, multi-step workflows using Python and LLM orchestration frameworks like LangChain and AutoGen.
• Implement RAG-based applications, prompt engineering, and fine-tuning for LLMs such as OpenAI, Gemini, and Llama.
• Integrate LLM APIs with vector databases, tool-based agents, and function calling to connect models to external data sources.
• Ensure the performance, scalability, and reliability of deployed AI systems while collaborating with cross-functional teams.

Required Skills

• 5+ years of software development experience, primarily in Python.
• 3+ years of experience designing, building, and deploying production ML systems.
• Hands-on experience with LLM orchestration frameworks, specifically LangChain and AutoGen.
• Strong understanding of Agentic AI, including planning, reasoning, and memory management.
• Proficiency in prompt engineering, instruction design, and RAG architectures.
• Experience building data pipelines and handling large-scale datasets.
• Strong grasp of machine learning concepts, applied statistics, and data structures.

Preferred Skills

• Experience with AWS cloud services (ECS/EKS, Lambda, S3, SageMaker) and containerization (Docker, Kubernetes).
• Familiarity with Infrastructure as Code tools like Terraform or CloudFormation.
• Experience with workflow orchestration using Step Functions.

Key Skills

Education

Any Graduate