We are seeking a Middle/Senior NLP Specialist to design, build, and optimize the text-processing, document intelligence, and language-driven services that power ProVision.
You’ll work closely with back-end engineers, front-end engineers, QA, and DevOps to deliver reliable, scalable, and secure NLP-enabled systems serving global enterprise clients.
The ideal candidate will bring strong experience in Python, NLP libraries, document parsing, information extraction, search/retrieval, and textual data transformation, with a focus on performance, maintainability, and production-grade architecture. Experience integrating LLM-powered workflows into enterprise applications is highly desirable.
What You’ll Be Doing
- Integrate large language models (LLMs) into core product workflows, with emphasis on reliability, performance, and guardrails against errors;
- Collaborate with engineers, product managers, and QA to deliver AI-driven features aligned with client needs;
- Optimize model serving and inference pipelines for low latency and cost efficiency in AWS (ECS, Lambda, S3, CloudWatch);
- Develop data pipelines for training and evaluation, leveraging existing stores (PostgreSQL, Redis, Elasticsearch/OpenSearch, S3);
- Ensure application components meet scalability, security, and compliance requirements for enterprise SaaS deployments;
- Stay current on advancements in NLP, LLMs, and applied ML; bring innovations into production when appropriate;
- Contribute to documentation, code reviews, and knowledge sharing across the engineering organization.
Must-Have Requirements
- 3+ years of proven experience as an NLP Engineer, Machine Learning Engineer (NLP focus), or Back-End Engineer with significant NLP experience in a SaaS or production environment;
- Strong proficiency in Python 3.10+;
- Strong experience with NLP libraries and frameworks for text processing, tokenization, entity extraction, embeddings, or semantic search;
- Experience working with document-heavy or unstructured text data;
- Familiarity with asynchronous processing and the AWS ecosystem (ECS, Lambda, S3, RDS, SQS/SNS);
- Competence in Git, CI/CD, and Agile/Scrum development;
- Strong problem-solving and debugging skills with an emphasis on performance, reliability, and output quality;
- Experience evaluating and improving the quality of text extraction, classification, or retrieval pipelines;
- English at a level (B2+) sufficient for daily communication with the team.
Preferred Requirements
- Experience with PostgreSQL, Redis, and/or Elasticsearch/OpenSearch;
- Experience with .NET;
- Experience with LLM application development, including prompting, RAG workflows, embeddings, and model orchestration;
- Familiarity with spaCy, NLTK, Hugging Face, sentence-transformers, LangChain, LlamaIndex, or equivalent tooling;
- Experience with PDF, Word, and OCR/text extraction pipelines, including libraries such as pdfplumber, PyPDF2, python-docx, docxtpl, or equivalent;
- Experience working with legal, financial, or other highly structured professional documents.
Personal Attributes
- Pragmatic engineer with a focus on reliability, experimentation, and clean architecture;
- Analytical and detail-oriented problem-solver with strong judgment on trade-offs between model quality, latency, and maintainability;
- Collaborative and communicative in cross-functional Agile teams;
- Proactive in improving data pipelines, extraction quality, and developer experience.
How We Work
- Our teams work in Agile Scrum squads, supported by strong CI/CD, IaC (Terraform/Terragrunt), and security-first practices (SOPS, KMS);
- All requirements live in Confluence, all work items live in Jira.
We offer
- Maximum flexibility;
- Professional trainings, conferences and certifications;
- Corporate events and benefits;
- Professional literature;
- English courses.
If you are interested, please let us know job@zfort.com