The Role We're looking for an Agentic Software Engineer (Full-Stack) to help us ship reliable, user-facing AI agent products to production - fast. You'll work at the intersection of modern AI tooling and strong software engineering discipline, building agentic experiences that our customers and internal teams rely on every day. This is not a research role. You will own production systems end-to-end: designing agent architectures, writing and reviewing code (often with agentic coding assistants), setting up rigorous evals, and operating what you build. If you care about making AI agents that actually work - not just demo well - this role is for you. What You'll Do - Build and Ship Agentic Applications Design, develop, and deliver agentic products end-to-end - including chat-based interfaces, AI workflow tools, and internal copilots - that serve real users in production. - Leverage Agentic Coding Workflows Use modern agentic coding tools daily (e.g., Claude Code, Codex, Cursor, and similar assistants) to accelerate delivery while maintaining high code quality and engineering standards. - Design Agent Systems Architect agent internals: tool calling, multi-step orchestration, memory and state management, retrieval pipelines, permissions models, and failure recovery strategies. - Own Evals and Quality Build and maintain agent evaluation infrastructure - regression suites, scenario-based tests, golden traces, and both offline and online metrics - so you always know whether your agent got better or worse. - Implement Observability Instrument agents with production-grade observability: distributed tracing, prompt and version tracking, tool-call telemetry, and cost/latency monitoring. - Own Production Readiness Take responsibility for the full lifecycle: rollout plans, QA, guardrails, incident response, and continuous improvement of deployed agents. What You Bring (Must-Haves) - Proven full-stack engineering ability. You've shipped production software end-to-end - not just prototypes or demos. - Hands-on experience building LLM-powered agents that work in production. You've owned at least 1–2 agentic features or products through deployment and operation. - Deep familiarity with agentic coding best practices. You understand task decomposition, agent delegation, prompt hygiene, iterative loops, and how to review and steer agentic outputs effectively. - Practical experience with agent evals and tracing. You've gone beyond model benchmarking to build evaluation systems specifically for agent behavior - including trace-based debugging and regression detection. - Solid engineering fundamentals. Testing, debugging, security basics, performance optimization, and reliability are second nature to you. Nice-to-Haves - Proficiency in TypeScript/Node.js and/or Python, with experience in modern web stacks and startup-pace delivery. - Familiarity with agent tooling ecosystems: prompt/version stores, eval harnesses, tracing and telemetry platforms (OpenTelemetry, LangSmith, Datadog, Honeycomb, or similar). - Experience with RAG architectures: vector databases, indexing strategies, chunking approaches, and retrieval evaluation. - Experience designing tool APIs for agents: structured output schemas, idempotency, rate limiting, and error handling patterns that make agents more reliable. Why Specright - Entrepreneurial culture. We're fast-paced, informal, and flat - collaboration and innovation matter more than hierarchy or fear of mistakes. - Real impact. Your work will power AI capabilities that touch real supply chain decisions across major industries. - Autonomy and ownership. We hire senior people and trust them to make decisions, ship fast, and continuously improve what they build. - Global team. You'll collaborate across time zones with talented colleagues who care about craft. - Competitive perks. Competitive salaries, flexible work hours, and a full benefits package (Medical, Vision, and Dental). About Specright Specright is the first purpose-built, patented platform for Specification Management. Whether it's packaging, raw materials, formulas, products, or machines, Specright helps companies digitize, map, and take action across their supply chain to reduce costs, increase profitability, and drive sustainability. Specright serves customers across industries, including packaging, food and beverage, consumer packaged goods, pharmaceutical, retail, industrials, and more. Recognized as a leader in Specification Management, Specright was named to the Deloitte Fast Technology 500 list in 2024, one of Fast Company's Most Innovative Companies for 2023, had three executives honored as Supply & Demand Chain Executive Pros to Know in 2023, and won Food Logistics' 2022 Top Software & Technology Provider award. For more information, visit: www.specright.com. We are an energetic company with an entrepreneurial, informal, versatile, intelligent, and fast-paced culture. We promote an open and relatively flat organization with an emphasis on collaboration, sharing ideas, and information. It's more important to innovate than to worry about making mistakes. Specright is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.

The Role We're looking for an Agentic Software Engineer (Full-Stack) to help us ship reliable, user-facing AI agent products to production - fast. You'll work at the intersection of modern AI tooling and strong software engineering discipline, building agentic experiences that our customers and internal teams rely on every day. This role is fully remote and based in Cairo, Egypt. This is not a research role. You will own production systems end-to-end: designing agent architectures, writing and reviewing code (often with agentic coding assistants), setting up rigorous evals, and operating what you build. If you care about making AI agents that actually work - not just demo well - this role is for you. What You'll Do - Build and Ship Agentic Applications Design, develop, and deliver agentic products end-to-end - including chat-based interfaces, AI workflow tools, and internal copilots - that serve real users in production. - Leverage Agentic Coding Workflows Use modern agentic coding tools daily (e.g., Claude Code, Codex, Cursor, and similar assistants) to accelerate delivery while maintaining high code quality and engineering standards. - Design Agent Systems Architect agent internals: tool calling, multi-step orchestration, memory and state management, retrieval pipelines, permissions models, and failure recovery strategies. - Own Evals and Quality Build and maintain agent evaluation infrastructure - regression suites, scenario-based tests, golden traces, and both offline and online metrics - so you always know whether your agent got better or worse. - Implement Observability Instrument agents with production-grade observability: distributed tracing, prompt and version tracking, tool-call telemetry, and cost/latency monitoring. - Own Production Readiness Take responsibility for the full lifecycle: rollout plans, QA, guardrails, incident response, and continuous improvement of deployed agents. What You Bring (Must-Haves) - Proven full-stack engineering ability. You've shipped production software end-to-end - not just prototypes or demos. - Hands-on experience building LLM-powered agents that work in production. You've owned at least 1–2 agentic features or products through deployment and operation. - Deep familiarity with agentic coding best practices. You understand task decomposition, agent delegation, prompt hygiene, iterative loops, and how to review and steer agentic outputs effectively. - Practical experience with agent evals and tracing. You've gone beyond model benchmarking to build evaluation systems specifically for agent behavior - including trace-based debugging and regression detection. - Solid engineering fundamentals. Testing, debugging, security basics, performance optimization, and reliability are second nature to you. Nice-to-Haves - Proficiency in TypeScript/Node.js and/or Python, with experience in modern web stacks and startup-pace delivery. - Familiarity with agent tooling ecosystems: prompt/version stores, eval harnesses, tracing and telemetry platforms (OpenTelemetry, LangSmith, Datadog, Honeycomb, or similar). - Experience with RAG architectures: vector databases, indexing strategies, chunking approaches, and retrieval evaluation. - Experience designing tool APIs for agents: structured output schemas, idempotency, rate limiting, and error handling patterns that make agents more reliable. Why Specright - Entrepreneurial culture. We're fast-paced, informal, and flat - collaboration and innovation matter more than hierarchy or fear of mistakes. - Real impact. Your work will power AI capabilities that touch real supply chain decisions across major industries. - Autonomy and ownership. We hire senior people and trust them to make decisions, ship fast, and continuously improve what they build. - Global team. You'll collaborate across time zones with talented colleagues who care about craft. - Competitive perks. Competitive salaries, flexible work hours, and a full benefits package (Medical, Vision, and Dental). About Specright Specright is the first purpose-built, patented platform for Specification Management. Whether it's packaging, raw materials, formulas, products, or machines, Specright helps companies digitize, map, and take action across their supply chain to reduce costs, increase profitability, and drive sustainability. Specright serves customers across industries, including packaging, food and beverage, consumer packaged goods, pharmaceutical, retail, industrials, and more. Recognized as a leader in Specification Management, Specright was named to the Deloitte Fast Technology 500 list in 2024, one of Fast Company's Most Innovative Companies for 2023, had three executives honored as Supply & Demand Chain Executive Pros to Know in 2023, and won Food Logistics' 2022 Top Software & Technology Provider award. For more information, visit: www.specright.com. We are an energetic company with an entrepreneurial, informal, versatile, intelligent, and fast-paced culture. We promote an open and relatively flat organization with an emphasis on collaboration, sharing ideas, and information. It's more important to innovate than to worry about making mistakes. Specright is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.

• As a Senior Software Engineer, Integrations, you will architect and build the systems that make these connections robust, observable, and extensible. • Design and implement HL7 v2 transformation pipelines — parsing, normalizing, enriching, and routing ADT, ORM, ORU, SIU, and MDM message types across heterogeneous RIS and EHR systems with non-standard vendor extensions. • Build and maintain integration connectors for modern and legacy imaging center RIS systems. • Architect fault-tolerant message queuing and delivery infrastructure for inbound and outbound HL7 and API traffic. • Develop interfaces for demand-side EHR integrations, including mapping from internal data models to FHIR-compliant (and other standards) representations. • Build and maintain REST API integrations with third-party referral sources, attorney platforms, and demand aggregators, including OAuth flows, rate limiting, retry logic, and schema versioning. • Own the observability layer for the integration infrastructure: structured logging, alerting on message processing latency/failures, and dashboards that surface issues before they reach the operations teams. • Contribute to the design of integration onboarding tooling that reduces time-to-live for new imaging center and referral source connections. • Provide technical mentorship to mid-level engineers and participate in architecture reviews across the broader Engineering org.

• Design and implement multi-file coding tasks across bug fixing, feature development, refactoring, and testing • Write clear natural-language specifications and reference implementations • Develop and extend unit and integration test suites • Review peer-generated tasks for correctness, clarity, and realism • Identify edge cases, ambiguities, and potential failure modes • Ensure alignment between specifications, code, and expected outputs