We’re hiring a
full/part-time Agent Builder
to design, implement, and optimize AI‑driven data workflows that support research and operational intelligence across biological, chemical, and healthcare datasets.
What You’ll Work On
Building and maintaining
AI agents
using frameworks like
LangChain, LangGraph, or OpenAI Assistants API
Designing retrieval‑augmented generation (RAG)
and other retrieval workflows
Developing
data pipelines
that handle structured and unstructured data from scientific, clinical, and bioinformatics sources
Curating and preprocessing datasets
from papers, repositories, and databases for downstream agent use
Implementing
feature extraction
and data labeling systems to convert text and tables into usable agent knowledge
Working with
cloud infrastructure
(AWS or GCP) to manage data storage, retrieval, and compute tasks
Writing robust
Python
code for automation, evaluation, and multi‑step reasoning
Collaborating closely with the founding team to deploy and refine production‑grade agents
Requirements
Strong proficiency in
Python
Hands‑on experience with LLM frameworks (LangChain, LangGraph, OpenAI API, etc.)
Background in
data engineering or bioinformatics
(preferred)
Experience with
RAG, vector databases, or semantic search
Familiarity with AWS or GCP , API integrations, and workflow orchestration
Ability to curate and analyze
scientific or healthcare datasets
Independent, analytical, and detail‑oriented mindset
Full‑time, part‑time remote
Paid position
To apply: attach your resume directly here or email kian@excipy.com
#J-18808-Ljbffr
full/part-time Agent Builder
to design, implement, and optimize AI‑driven data workflows that support research and operational intelligence across biological, chemical, and healthcare datasets.
What You’ll Work On
Building and maintaining
AI agents
using frameworks like
LangChain, LangGraph, or OpenAI Assistants API
Designing retrieval‑augmented generation (RAG)
and other retrieval workflows
Developing
data pipelines
that handle structured and unstructured data from scientific, clinical, and bioinformatics sources
Curating and preprocessing datasets
from papers, repositories, and databases for downstream agent use
Implementing
feature extraction
and data labeling systems to convert text and tables into usable agent knowledge
Working with
cloud infrastructure
(AWS or GCP) to manage data storage, retrieval, and compute tasks
Writing robust
Python
code for automation, evaluation, and multi‑step reasoning
Collaborating closely with the founding team to deploy and refine production‑grade agents
Requirements
Strong proficiency in
Python
Hands‑on experience with LLM frameworks (LangChain, LangGraph, OpenAI API, etc.)
Background in
data engineering or bioinformatics
(preferred)
Experience with
RAG, vector databases, or semantic search
Familiarity with AWS or GCP , API integrations, and workflow orchestration
Ability to curate and analyze
scientific or healthcare datasets
Independent, analytical, and detail‑oriented mindset
Full‑time, part‑time remote
Paid position
To apply: attach your resume directly here or email kian@excipy.com
#J-18808-Ljbffr