Senior Applied AI & NLP Engineer

RedGraphs is hiring a

Senior Applied AI & NLP Engineer to build production AI systems that turn ambiguous corporate disclosures into evidence-backed, correctly attributed economic relationships. This is a senior engineering role for someone who has

owned production NLP, ML, information extraction, search, or LLM systems beyond internships, coursework, or prototypes . This is not a chatbot or prompt-engineering role. You will work on difficult real-world problems across

NLP, information extraction, retrieval, entity resolution, relationship attribution, LLMs, model evaluation, and deterministic validation .

About RedGraphs RedGraphs builds economic intelligence infrastructure that makes business relationships visible, measurable, and actionable. We transform evidence buried in regulatory filings, financial disclosures, and other primary-source corporate documents into structured, time-aware relationship data. Our Business Relationships Analytics dataset is jointly developed with S&P Global Market Intelligence and commercially licensed and delivered through S&P Global Market Intelligence. We are a small engineering team. Senior engineers are expected to understand the business meaning of the systems they build and own important problems from investigation through production verification.

What You Will Work On

• Improve relationship discovery and extraction from regulatory filings, financial disclosures, and corporate documents.
• Build and improve evidence retrieval, candidate generation, ranking, classification, and extraction systems.
• Improve entity identification, entity resolution, relationship attribution, and relationship direction.
• Handle difficult linguistic phenomena including negation, qualification, uncertain language, historical statements, indirect references, and multi-entity sentences.
• Extract and validate financial attributes, percentages, monetary values, dates, and other relationship metadata.
• Design systems combining LLMs, traditional NLP and ML, retrieval, classifiers, and deterministic validation.
• Determine when a probabilistic model is appropriate and when deterministic software provides the safer solution.
• Build reviewed evaluation datasets and regression suites based on real false positives and false negatives.
• Diagnose model failures at the mechanism level rather than treating aggregate accuracy as sufficient.
• Improve precision and recall while protecting already-correct behavior.
• Design structured model outputs that can be validated before publication.
• Preserve evidence provenance so outputs can be traced to the document and text that support them.
• Improve model inference reliability, latency, throughput, and cost where relevant.
• Work with platform engineers to move AI capabilities into reliable, observable production workflows.
• Own improvements through testing, deployment, and production verification.

What We Are Looking For

• Strong evidence of

senior-level technical ownership in applied machine learning, NLP, AI engineering, or closely related software systems.

• Typically

6+ years of relevant professional experience , or equivalent evidence of senior technical scope and ownership.

• Demonstrated ownership of

production NLP, ML, information extraction, search, or LLM systems beyond internships, coursework, or prototypes .

• Strong production Python engineering.
• Hands-on experience building NLP, machine learning, LLM, information extraction, search, or document-intelligence systems.
• Experience taking model behavior beyond notebooks and demos into tested production workflows.
• Strong understanding of model evaluation, error analysis, precision and recall tradeoffs, and regression testing.
• Ability to reason about ambiguous language and translate linguistic failure modes into engineering mechanisms.
• Strong software engineering fundamentals including testing, Git, Linux, APIs, and maintainable system design.
• Ability to investigate unfamiliar behavior independently and communicate findings clearly. A strong research background can be valuable, but it must be accompanied by evidence that you can

build, debug, deploy, and own real production software systems .

Particularly Relevant Experience Experience in one or more of the following is valuable:

• Relation extraction
• Named-entity recognition
• Entity linking or record linkage
• Information retrieval, semantic search, or reranking
• Retrieval-augmented generation
• Fine-tuning or model adaptation
• Structured generation and constrained outputs
• Model inference optimization or serving
• Evaluation against human-reviewed truth datasets
• Financial, legal, regulatory, scientific, or similarly complex documents
• Knowledge graphs or relationship-oriented data
• Weak supervision or difficult dataset-construction programs
• Combining deterministic rules with statistical or generative models
• Investigating hallucinations, unsupported outputs, attribution errors, or model calibration

This Role Is Not Primarily

• Chatbot development
• Prompt writing
• Generic GenAI application integration
• Research without production ownership
• Model experimentation without rigorous evaluation We are looking for someone who wants to make AI behavior

measurable, evidence-bound, explainable, and dependable .

Working Model This role is based in Delhi NCR, India. RedGraphs is building its India engineering team in Delhi NCR and plans to establish a collaborative development office there. The team currently works remotely while that office is being established. Candidates should be based in, or willing to relocate to, Delhi NCR and comfortable with regular in-person collaboration once the office is operational. The role also requires meaningful and consistent working overlap with the

US Eastern time zone .

Apply Read the full role and apply:

https://redgraphs.com/careers/senior\-applied\-ai\-nlp\-engineer/ Requisition: RG-0007