Role Description Our client is a small, fast-moving technology business focused on delivering practical, on-premise AI solutions to commercial customers. Their solutions run on dedicated AI servers and integrate: - Local LLMs (Ollama) - Retrieval Augmented Generation (RAG) - SQL-based ERP systems - Python (FastAPI) APIs - Open WebUI interfaces They are looking for an Intermediate AI / Full-Stack Developer who is hands-on, solution-oriented, and comfortable working across the full stack. This is not a narrow role — you’ll work directly on real production systems and gradually take ownership of a deployed AI solution, enhancing it over time and helping scale it to additional customers. Location: Remote (Durban-based candidates preferred for occasional in-person meetings) Qualifications - 2–5 years of practical software development experience - Strong SQL skills (joins, indexing, query optimisation, troubleshooting) - Python development experience (FastAPI or similar frameworks) - Experience building and maintaining REST APIs - Basic understanding of AI/LLMs (e.g. embeddings, prompt handling, or RAG concepts) - Version control (Git) - Experience with RAG pipelines or vector databases Requirements - Build and maintain Python (FastAPI) APIs for AI-driven applications - Design, optimise, and troubleshoot SQL queries against ERP systems - Implement and improve RAG pipelines using local LLMs (Ollama) - Integrate backend services with front-end interfaces (e.g. Open WebUI) - Diagnose and resolve production issues across data, APIs, and infrastructure - Support deployment and operational environments - Ensure data accuracy, system performance, and access control - Document system behaviour, decisions, and improvements clearly Benefits - 1 year contract (renewable) - Fully remote with occasional in-person collaboration - Monthly remuneration

• Build and maintain lightweight AI tools and agents to support internal teams and operational workflows. • Automate recurring processes across teams to reduce manual work and increase efficiency. • Develop internal scripts, services, and automations that unify workflows and data across the company. • Improve system reliability through better monitoring, error handling, and documentation. • Support internal data infrastructure by streamlining ingestion, transformation, and operational reporting workflows. • Collaborate with cross-functional teams to identify bottlenecks and design scalable, technical solutions. • Contribute to the ongoing development of NoGood’s AI-native Growth OS, helping shape how work is done across teams. • Evaluate new AI technologies and automation tools to enhance internal operations. • Document systems and provide internal training where needed. • Champion a mindset of technical excellence, efficiency, and continuous improvement.

Role Description RxBenefits is hiring! We are adding a Software Engineer III to the growing application development team at our Birmingham, AL headquarters. As a level III engineer, you will be responsible for creating the next generation of software at RxBenefits to support our rapidly growing business. You will also be a thought leader across the technology organization that champions the delivery of modern software. This is an exciting opportunity for a forward-thinking professional that is able to conceptualize, deliver, and support the technology that our employees and partners need to succeed. - Design, build, and maintain AI-driven backend services, APIs, pipelines, and application features. - Design AI pipelines with secure data handling, PII/PHI protection, redaction, and access-control-aware processing. - Design and implement document ingestion pipelines (PDFs, scans, images, email attachments). - Design evaluation frameworks for extraction accuracy, retrieval relevance, and LLM output quality. - Build document classification, entity extraction, and schema mapping workflows. - Implement OCR and layout-aware extraction pipelines. - Develop confidence scoring, human-in-the-loop workflows, and validation mechanisms. - Build systems that route extracted data into downstream enterprise systems. - Build connectors and ingestion pipelines for structured and unstructured systems (e.g., Confluence, file stores, databases). - Implement chunking, indexing, and metadata enrichment strategies. - Design retrieval strategies including hybrid search (vector + keyword). - Improve relevance via ranking, filtering, and contextualization. - Implement monitoring and observability for AI systems, including model performance, retrieval quality, extraction accuracy, and drift detection. - Partner with Product, Data, and Architecture teams to translate business problems into efficient AI solutions. - Participate in the design process to build efficient, scalable and maintainable architecture. - Research, evaluate and recommend alternative solutions. - Build scalable services integrating LLMs, retrieval systems, model inference endpoints, and third-party AI providers. - Ensure solutions meet enterprise standards for reliability, security, compliance, and observability. - Collect and analyze metrics to drive implementation decisions. - Design, improve and document processes. - Review and collaborate with other engineers on their code. - Support your team through encouragement and by example. - Mentor and share knowledge within the team and across the department. - Deliver on personal and team deadlines and goals. Qualifications - Bachelor's degree in computer science, mathematics, engineering or another related field. - 6-8 years of professional experience in application development. - Comfortable working with multiple programming languages at the same time. - Strong proficiency in one more backend languages: Java, Python, Go, or Node.js – Python is strongly preferred. - Hands-on experience implementing AI features such as: - Integrating LLM APIs. - Building embeddings, vector stores, or semantic search. - Fine-tuning prompt engineering for LLM-based systems. - Implementing Retrieval Augmented Generation (RAG) patterns. - Experience consuming or integrating machine learning models in production applications. - Experience with OCR and document AI platforms (Textract, Azure Form Recognizer, Google Doc AI, Tesseract, etc.). - Understanding of structured data extraction from semi-structured documents. - Experience with schema mapping / data normalization pipelines. - Knowledge of confidence scoring, validation, and exception handling. - Familiarity with event-driven data pipelines. - Experience designing search systems or knowledge retrieval platforms. - Understanding of information retrieval concepts (ranking, recall, precision, indexing). - Knowledge of document chunking and embedding strategies. - Familiarity with access control propagation in search systems. - Experience with monitoring ML/AI systems in production. - Understanding of model drift, data drift, and prompt performance tracking. - Experience handling sensitive data in AI workflows. - Understanding of data masking, redaction, or de-identification techniques. - Solid understanding of RESTful API design, microservices, and distributed systems. - Strong foundation in data structures, algorithms, concurrency, and performance optimization. - Familiarity with relational and NoSQL databases and performance considerations. - Experience with Agile development methodologies. - Strong communications and presentation skills. - Excellent organizational skills, detail-oriented, and works well in a team environment or as an independent contributor. - Ability to work with minimal supervision within a team environment. - Ability to think strategically and execute with urgency. - Desire to innovate and discover new technologies. - Driven to continually learn and master new skills. Preferred Skills/Experience - Experience working in regulated industries (healthcare, finance, insurance). - Knowledge of governance frameworks around data privacy (HIPAA, SOC2, GDPR, etc.). - Experience evaluating model performance, prompt effectiveness, and model drift. - Experience developing AI guardrails, moderation, hallucination-prevention, or safety patterns. - Extensive experience in web development using modern frontend and backend technologies. - Strong proficiency in frontend (React, NextJS) and backend (Python) technologies. - Work with responsive design frameworks. - Deployments to Amazon Web Services. - Proficiency in AWS services: EC2, S3, Lambda, RDS, CloudFormation/Terraform, ECS/EKS, VPC, IAM, etc. - Caching and in-memory database technologies. - Asynchronous/multi-threaded programming patterns. Benefits - Remote first work environment. - Choice of a HDHP or PPO Medical plan, we pay 100% of the premium for the HDHP for you and your eligible family members. - Dental, Vision, Short- and Long-Term Disability, and Group Life Insurance that we also pay 100% of premiums (for your family too on Dental and Vision). - Additional buy-up options for Short- and Long-Term Disability and Life Insurance. - 401(k) with an employer match up to 3.5% available after 60 days. - Community Service Day to give back and support what you love in your community. - 10 company holidays including MLK Day, Juneteenth, and the day after Thanksgiving plus a floating holiday to use as you like. - Reimbursements for high-speed internet, we’ll send you a computer and monitors to help you do your best work. - Tuition Reimbursement for accredited degree programs. - Paid New Parent Leave that can be used for adoption or birth. - Pet insurance to protect your furbabies. - A robust mental health benefit and EAP service through Spring Health to support you when you need it most.

• Build and extend the eval pipeline: how we measure task completion, catch regressions, and turn production failures into fixed behaviors. • Work on context management: what the agent sees, when, and how we keep long-horizon tasks coherent without burning tokens. • Design sub-agent patterns: when to fan out, how to compose specialized agents cleanly, and how to keep the parent agent in control of the outcome. • Own document parsing: turning supplier-uploaded invoices, catalogs, and contracts into structured context the agent can reason over. • Wrap Coupa supplier APIs as agent-callable CLI tools, with clean error surfaces and sensible defaults for an agent caller. • Ship supplier-facing skills on top of the harness: the procedural instructions and tool compositions that let the agent handle specific tasks end-to-end. • Debug messy production behavior: why did the agent take that path, where did it get confused, and what tool, context, or harness change fixes it? • Partner with the senior engineer on harness architecture calls as you find gaps while working across the stack.