Identity AI / ML Engineer

OpenKyber is a rapidly growing Information Technology company with a diverse portfolio of technology products and services and a large network of industry partnerships. With over 22 years of being a successful business with a global talent pool and presence, OpenKyber is a certified Microsoft Gold Partner and specializes in delivering expert Microsoft based solutions for technical and business needs. We have been recognized by Inc. 500 Magazine as one of the fastest growing small companies in the Unites States. we are a Tier 1 vendor for the City and County of San Francisco for Cloud Services, Staffing Services and Training Services. For this multi-year opportunity with a diverse set of needs to address, we are currently focusing on establishing partnerships with individuals as well as companies who can help us enhance our overall service portfolio, cut lead times, and ultimately help us deliver successfully. We currently hold sizable Government accounts in the San Francisco bay area including City and County of San Francisco, San Mateo County, and Santa Clara County. We take great pride in our global reach and local influence. Your experience alongside our highly skilled and talented internal team who guide you along the way, offers key insights into what helps you stand out in a competitive job market. If you are a partner company, please submit resumes with contact information of your own W2 Consultants only . Submitted consultants are expected to have excellent communication skills.

• Year 1 Internal Chatbot Refinement: UI improvements, user history & feedback 240 hours. Deliverables: Application code + Docker build; user profile & history DB; test cases & privacy/compliance pipeline.
• External Chatbot Development: Initial conversational bot (non-analytical) 480 hours. Deliverables: Application code + Docker build; conversation DB; test cases & compliance pipeline; UX/agency scoring.
• RPA: Local LLM analysis tools with batching 240 hours. Deliverables: Application code; integration documentation; usage & process reporting.
• Knowledge Retrieval (RAG & Search): Improve vector/hybrid search & case mgmt. integration 520 hours. Deliverables: Comparative RAG results; agent code/prompts; test pipeline; recommendations for knowledge store updates.
• Translation: MD-specific terminology & guidelines 80 hours. Deliverables: Translation agent code/prompts; test cases & pipeline.
• Transcription: Refine deployment based on feedback 160 hours. Deliverables: Comparative pipeline results; updated code/prompts; test cases & pipeline.
• Redaction (PII & Sensitive Data): Build detection agent 240 hours. Deliverables: Application code; test cases & pipeline for PII/sensitive data identification.
• Year 2 Internal Chatbot Refinement: Personalization & workflow integration 160 hours. Deliverables: Application code + Docker build; test cases & compliance pipeline.
• External Chatbot Development: Improvements from feedback 160 hours. Deliverables: Application code + Docker build; test cases & compliance pipeline.
• RPA: Reporting pipelines & analytics; automate tasks 160 hours. Deliverables: Application code; integration docs; usage & process reporting.
• Knowledge Retrieval: Expand case mgmt integration & permission-based indexing - 240 hours. Deliverables: Comparative RAG results; agent code/prompts; test pipeline; knowledge store recommendations.
• Deep Research Capabilities: graphRAG for case statute interaction 520 hours. Deliverables: Web/file crawler to graph format; agent code/prompts; test pipeline; knowledge store recommendations.
• Translation: Quality & accuracy improvements 80 hours. Deliverables: Translation agent code/prompts; test cases & pipeline.
• Transcription: Improve diarization & speaker ID 160 hours. Deliverables: Transcription agent code/prompts; test cases & pipeline.
• Redaction: Accuracy improvements & workflow integration 160 hours. Deliverables: Application code; test cases & pipeline.
• Document Analysis: NLP + graphRAG to reduce token use 320 hours. Deliverables: Scripts for universal intermediary format; extraction scripts to graph store.
• Year 3 Internal Chatbot Refinement: Improvements from feedback 160 hours. Deliverables: Application code + Docker build; test cases & compliance pipeline.
• External Chatbot Development: County-specific deployments & scalability 200 hours. Deliverables: County data ingestion; agent/bot revisions; onboarding; county-specific test pipeline.
• RPA: Case update review & flagging 320 hours. Deliverables: Application code; integration docs; usage & process reporting.
• Knowledge Retrieval: Centralize statutes/ordinances for counties 320 hours. Deliverables: Document data sources; standardization recommendations; supporting code/database.
• Deep Research Capabilities: Combine retrieval + case mgmt for complex research 320 hours. Deliverables: Agent code/prompts; test pipeline; knowledge store recommendations.
• Translation: Expand language support 80 hours. Deliverables: Translation agent code/prompts; test cases & pipeline.
• Transcription: Expand language support 80 hours. Deliverables: Transcription agent code/prompts; test cases & pipeline.
• Document Analysis: Extract structured data from forms 160 hours. Deliverables: Extraction scripts; standardized process proposal; supporting tools.
• Document Generation: Initial PDF generation features 320 hours. Deliverables: PDF generation scripts; agent code/prompts; test pipeline.
• Year 4 Internal Chatbot Refinement: Low-code custom agent builder 320 hours. Deliverables: Application code + Docker build; test cases & compliance pipeline.
• External Chatbot Development: Workflow-integrated chatbot 320 hours. Deliverables: Application code + Docker build; test cases & compliance pipeline.
• RPA: Expand AI-enhanced reporting & automation 200 hours. Deliverables: Application code; integration docs; usage & process reporting.
• Knowledge Retrieval: Finetune embeddings & small LLM 320 hours. Deliverables: Finetuning scripts; model weights.
• Deep Research Capabilities: Limited web access for research 240 hours Deliverables: Agent code/prompts; test pipeline; knowledge store recommendations.
• Transcription: Finetune model for opt-in user voices 240 hours. Deliverables: Voice finetuning scripts; model weights.
• Document Generation: Expand document types & form-filling 320 hours. Document/presentation generation scripts; agent code/prompts; test pipeline.
• Year 5 Internal Chatbot Refinement: Improvements from feedback 160 hours. Deliverables: Application code + Docker build; test cases & compliance pipeline.
• External Chatbot Development: Feature expansion 160 hours. Deliverables: Application code + Docker build; test cases & compliance pipeline.
• RPA: Integrate retrieval & research into workflows (with manual review) 480 hours Deliverables: Application code; integration docs; usage & process reporting.
• Knowledge Retrieval: Open some retrieval capabilities to public bot 320 hours. Deliverables: Application code; integration docs; usage & process reporting.
• Transcription: Integrate into court recording systems 320 hours. Deliverables: Application code; integration docs; usage & process reporting.
• Document Generation: Modify user documents using RPA/retrieval/research 520 hours. Deliverables: Document-modification agent code/prompts; test pipeline.

• Bachelor of Science in Engineering, Computer Science, Data Science, or Mathematics, or a related field (as determined by the AOC).
• At least three (3) years' experience in data science, machine learning, or applied AI development.
• At least three (3) years' experience in software engineering, architecture, or web development.
• Experience with: SQL and relational database systems (e.g., PostgreSQL) Fine-tuning small language models or embedding models Contributing to or maintaining open-source software projects Graph databases or graph extensions (e.g., Neo4j, Apache AGE) Designing and implementing multi-agent or task-oriented AI systems Embedding models, vector similarity, re-ranking, and graph retrieval techniques in RAG systems Version control systems (e.g., Git), containerization technologies (e.g., Docker), and service-oriented architectures Collaborating with large language models (LLMs), including both API-based integration and local deployment Validating AI-generated outputs, mitigating hallucinations, and integrating AI tools into production service pipelines Ability to: Understand data structures, algorithms, and clean coding principles Select and apply appropriate techniques (LLM and non-LLM) based on task requirements Develop and improve testing and evaluation pipelines for AI systems, including use of synthetic data Demonstrate proficiency in Python, including the ability to develop production grade backend services, APIs, middleware, and data pipelines. Design and implement AI/ML systems that operate effectively on complex, inconsistent, or evolving datasets while balancing accuracy, latency, and cost (token consumption) Collaborate with team members to define system architecture, agent workflows, and data pipelines while working in constrained environments, including limited GPU availability and predefined infrastructure Knowledge of: Hybrid cloud environments and distributed system considerations Threading, asynchronous processing, and queues in backend servers React and Microsoft Teams Toolkit for developing chatbot user interfaces Non-llm data analysis techniques for structured, semi-structured, and unstructured data Classical natural language processing (NLP) techniques in addition to LLM-based approaches Data science and LLM-related libraries in Rust or other performance-oriented programming languages

For applications and inquiries, contact: hirings@openkyber.com