Data Scientist

HireTalent - Staffing & Recruiting Firm; United States; On-site; USD 100,000 - 130,000; Part time

Job summary

A recruitment agency in the United States is seeking a Mid-Senior Level Data Scientist to design and deploy retrieval-grounded LLM systems. This role involves building pipelines for large datasets, processing complex documents, and integrating web-based data sources. Candidates should have over 4 years of experience in data science or ML, with strong skills in NLP, Python, and SQL. This contract position is ideal for those who enjoy technical challenges and impactful projects.

Qualifications

• 4+ years of experience in data science or applied ML with a focus on NLP and GenAI.
• Strong hands-on experience building LLM-based retrieval or information extraction systems.
• Proficiency in Python and SQL, with an engineering mindset.

Responsibilities

• Designing and deploying retrieval-grounded LLM systems.
• Building pipelines to ingest and transform large datasets.
• Processing complex documents using OCR and layout-aware parsing.

Skills

NLP and GenAI

Python

SQL

Data analysis

Information extraction systems

Tools

OpenAI

Google GenAI

LangChain

Elasticsearch

Databricks

Job description

We’re working with a Client that’s building real, production-grade LLM systems to power growth analytics and strategic decision-making. This team isn’t experimenting in notebooks. They’re deploying retrieval‑grounded AI at scale, working with large, messy document datasets, and setting standards for how GenAI is used in a regulated environment.

If you enjoy owning systems end to end and care about accuracy, grounding, and impact, this role is worth a look.

What You’ll Be Working On

• Designing and deploying retrieval‑grounded LLM systems, from standard to advanced RAG patterns
• Building pipelines to ingest, transform, and normalize large internal and public datasets
• Processing complex documents including PDFs, HTML, and scanned content, using OCR, layout‑aware parsing, and table extraction
• Developing LLM‑driven information extraction workflows with structured outputs, validation, and accuracy evaluation
• Owning the full retrieval stack: chunking strategies, embeddings, indexing, hybrid retrieval, reranking, and relevance tuning
• Integrating web‑based data sources with safeguards like retries, rate limiting, and change detection
• Establishing evaluation and monitoring practices to ensure grounded, reliable outputs in production
• Partnering closely with analytics and business stakeholders to turn ambiguous questions into measurable outcomes

What You Bring

• 4+ years of experience in data science or applied ML, with deep focus on NLP and GenAI
• Strong hands‑on experience building LLM‑based retrieval or information extraction systems used in real‑world production settings
• Proficiency in Python and SQL, with a strong engineering mindset
• Solid experience with Databricks, Spark, and lakehouse architectures
• Deep understanding of vector search concepts including embeddings, hybrid retrieval, and reranking
• Experience working with semi‑structured and unstructured data such as PDFs, tables, forms, and web content
• A strong grasp of grounding, attribution, and evaluation techniques that reduce hallucinations
• Ability to clearly communicate tradeoffs and recommendations to both technical and non‑technical partners

Tools & Tech You’ll Use

• LLM and orchestration frameworks: OpenAI, Google GenAI, LangChain, LangGraph
• Retrieval and vector tooling: FAISS, Elasticsearch/OpenSearch, Pinecone, Weaviate, Milvus, Chroma

Nice to Have

• Experience with agentic workflows and tool‑calling patterns
• Background working in regulated environments with governance, auditability, and access controls

Why This Role

You’ll be joining a team that treats GenAI as a core capability, not a side project. The work is technical, impactful, and highly visible, with real ownership from ingestion to production.

If you’re excited about building reliable LLM systems that actually get used, this is a strong next step.

Seniority level

• Mid‑Senior level

Employment type

• Contract

Job function

• Engineering and Analyst

Industries

• Hospitals and Health Care, Public Health, and Insurance