NLP Scientist

BEPC is actively looking for NLP Scientist, in South San Francisco, CA area!

W2 Contract – 6 months with possible extensions!

Benefits include medical, dental, vision, and life insurance

Pay Rate: $75.23 - $83.23/hour - Determined based on experience (Paid Weekly)

Work Model: Hybrid role – Candidates must be able to work onsite 1–2 days per week at the South San Francisco, CA site.

Focus: Evidence-Grounded Retrieval, Entailment and Claim Verification.

Note: This is a W2 only role — C2C, C2H will not be considered

Summary of the Role:

BEPC is seeking a highly motivated NLP Scientist to join our client’s site in South San Francisco, CA. This role will support the development of a capability that checks generated claims against approved evidence before they reach a human reviewer.

Given a statement and a corpus of approved claims, product labeling, clinical study results, and references, the system retrieves the relevant evidence, decomposes compound statements into checkable assertions, tests whether the evidence supports each one, and returns a decision with citations a reviewer can follow.

A large part of the value is knowing when to refuse: the system must distinguish a directly supported claim from one supported only with a qualifier, one the evidence contradicts, and one where evidence is insufficient, and abstain rather than guess.

This capability assists Medical, Legal, and Regulatory review; it does not replace that review or approve content.

Summary of Duties and Responsibilities:

• \n
• Build capabilities that check generated claims against approved evidence before they reach a human reviewer.
• \n
• Retrieve relevant evidence from approved claims, product labeling, clinical study results, and references.
• \n
• Decompose compound statements into checkable assertions.
• \n
• Test whether evidence supports each assertion.
• \n
• Return decisions with citations that reviewers can follow.
• \n
• Distinguish between directly supported claims, claims supported only with a qualifier, contradicted claims, and claims where evidence is insufficient.
• \n
• Design the system to abstain rather than guess when evidence is insufficient.
• \n
• Support Medical, Legal, and Regulatory review without replacing human review or approving content.
• \n

Main Qualifications:

Education: Bachelor’s degree required.

• \n
• Strong Python production engineering with modern natural language processing frameworks.
• \n
• Demonstrated work in evidence-grounded NLP: hybrid retrieval, natural-language inference and entailment, claim decomposition, and evidence attribution.
• \n
• Has measured whether answers were genuinely supported by their cited source, not only that a retrieval pipeline returned something.
• \n
• Experience with scientific, technical, or regulatory source material, studies, specifications, publications, labeling, or contracts.
• \n
• Experience building expert-labeled evaluation datasets, including annotation guidelines and inter-annotator agreement.
• \n
• Reports error rates by direction, not only aggregate accuracy, false approval and false rejection carry very different costs.
• \n
• Experience with human-in-the-loop design: confidence thresholds, abstention, escalation rules, and safe failure behavior.
• \n
• Experience building traceable systems where a past decision can be reconstructed from its model version, evidence set, and reviewer action.
• \n
• Experience with vector and lexical retrieval, model APIs, and production evaluation infrastructure.
• \n
• Ability to work with legal and regulatory stakeholders and treat process constraints as design requirements.
• \n

Preferred Qualifications:

• \n
• Experience combining deterministic rules with model judgment in a single decision system.
• \n
• Experience with knowledge graphs linking claims, evidence, references, products, and indications.
• \n
• Experience in any regulated or high-stakes review environment, legal, financial compliance, scientific publishing, or fact-checking.
• \n
• Familiarity with study design, statistical evidence, and citation practice.
• \n
• Pharmaceutical or life-sciences experience is welcome but not required, domain context and review workflow will be provided.
• \n

About BEPC

BEPC Inc., founded in 2007, is a 100% employee-owned company providing top-tier consulting and staffing solutions across industries like technology, engineering, manufacturing, and project management. At BEPC, we are driven by innovation and a commitment to excellence. We take pride in fostering a collaborative and innovative environment where our team members thrive. With competitive benefits, including medical, dental, vision, and life insurance, BEPC is dedicated to supporting our employees' personal and professional growth.

Apply Now!

Qualified candidates are encouraged to apply by submitting an up-to-date resume that highlights how your experience aligns with the role. Please include specific examples that demonstrate your qualifications. We look forward to connecting with you!