3 weeks left to apply
Job Description
?? Key Responsibilities : Build and deploy LLMs (e.g., Anthropic Claude) on AWS Bedrock using boto3. Fine-tune LLMs on AWS SageMaker using HuggingFace Transformers and LoRA techniques. Design and optimize prompt engineering workflows using LangChain . Develop RAG pipelines integrated with AWS OpenSearch and LangChain for high-accuracy retrieval. Build intelligent AI agents using crew.ai or autogen , deployed via AWS Lambda . Implement agentic automation workflows using n8n , including custom workflow orchestration. Containerize and deploy applications using Docker on Amazon ECS/EKS . Monitor and optimize model/application performance using Amazon CloudWatch and Weights & Biases (wandb) . ? Must-Have Skills : 5+ years of Python development experience and 2+ years in GenAI/LLM projects . Strong experience with: AWS Bedrock, SageMaker, Lambda, boto3 HuggingFace Transformers, LoRA LangChain, RAG pipelines crew.ai / autogen n8n workflow automation wandb for experiment tracking Solid understanding of Docker, container orchestration, and cloud deployments. Ability to build production-ready GenAI pipelines end-to-end. ?? Preferred Skills : AWS Certifications (Machine Learning Specialty, Solutions Architect). Familiarity with llamaindex and pre-built n8n templates . Experience with MLOps, vector databases, and observability tools.
Additional Information
- Company Name
- Hellowork Consultants
- Industry
- N/A
- Department
- N/A
- Role Category
- AI Engineer
- Job Role
- Mid-Senior level
- Education
- No Restriction
- Job Types
- Remote
- Gender
- No Restriction
- Notice Period
- Less Than 30 Days
- Year of Experience
- 1 - Any Yrs
- Job Posted On
- 3 days ago
- Application Ends
- 3 weeks left to apply
Similar Jobs
3 weeks ago
Full Stack Developer ? AI Native Product Builder
Whitecarrot.io
Quick Apply
Upload your resume to apply for this position