Job Overview

key responsibilities:

1. agentic ai systems : design and implement intelligent agentic ai systems using llms, vector databases, and orchestration frameworks.

2. ml workflows : build, deploy, and maintain ml workflows using aws sagemaker, lambda, and ec2 with docker.

3. etl pipelines : develop and manage etl pipelines using aws glue and integrate with structured/unstructured data sources.

4. full-stack development : implement apis and full-stack components to support ml agents, including visualization tools using streamlit.

5. legacy system integration : reverse-engineer existing codebases and apis to integrate ai features into legacy or proprietary systems.

required qualifications:

1. aws experience : hands-on experience with aws services like lambda, ec2, glue, and sagemaker.

2. python and full-stack development : strong python and full-stack development experience.

3. llms and vector search : solid grasp of llms and vector search engines.

4. reverse-engineering : demonstrated ability to reverse-engineer systems and build integrations.

5. cloud infrastructure : experience with cloud infrastructure, restful apis, ci/cd pipelines, and containerization.

preferred qualifications:

1. rag and multi-agent systems : background in retrieval-augmented generation (rag), multi-agent systems, or knowledge graphs.

2. open-source llm frameworks : experience with open-source llm frameworks like hugging face.

3. autonomous task planning : knowledge of autonomous task planning, symbolic reasoning, or reinforcement learning.

4. secure ai systems : exposure to secure, regulated, or enterprise-scale ai systems.

this role requires a strong blend of technical skills, including aws, python, and full-stack development, as well as experience with llms, vector search, and agentic ai systems.