Job Description & Details
This is a hands-on technical role for someone who has moved past building basic chatbot wrappers and is actually shipping production-grade RAG pipelines and autonomous AI agents. If you enjoy wrangling messy data and hooking it up to LLMs like GPT-4 or Claude while solving latency and hallucination problems, this gig is right in your wheelhouse.
What You'll Actually Be Doing
You'll spend your days designing and optimizing document ingestion pipelines, converting text into embeddings, and storing them in vector databases for lightning-fast retrieval. A big chunk of your time will go toward building autonomous AI agents using frameworks like LangChain or CrewAI, and making sure the underlying Python microservices scale cleanly in the cloud, preferably on Azure.
The Core Tech Stack
You need to be fluent in Python, SQL, and PySpark, with solid experience operating inside Databricks. On the GenAI side, deep familiarity with Large Language Models, vector DBs like Pinecone or Weaviate, and advanced RAG architectures are non-negotiable. If you've also worked with healthcare data domains like claims or clinical records, that's a massive bonus.
Interview Expectations
Expect the technical interviewers to grill you on how you handle context windows and reduce latency in heavy RAG architectures. They'll likely ask you to debug a scenario where an AI agent loops infinitely or hallucinates incorrect data, and they want to see if you instinctively implement guardrails and evaluation metrics rather than just crossing your fingers.
Application Advice
Make sure your resume doesn't just list buzzwords; highlight specific projects where you built vector search architectures or deployed LLMs to production. Explicitly call out your experience with Databricks, PySpark, and frameworks like LangChain or AutoGen so the ATS instantly flags you as a hands-on engineer who can code, not just talk strategy.