Software Engineer II in Over

Call Box exists to grow people. We believe that everyone wants to become a better version of themselves, and we work hard to provide software and a culture that maximises that growth mindset. We hire smart and ambitious doers in order to set them loose in an exciting and complex technology business where they will build, sell, and deploy Artificial Intelligence solutions that help our clients grow their bottom line. We are building a high-performance, AI-native engineering organisation. We have a small team with high output and autonomous execution. This individual contributor role involves shipping and owning your services. You will build features, write production code daily, and solve hard problems in real-time AI systems. With high autonomy you can have high impact. We are building a conversational voice AI system for the automotive industry. The product processes real-time voice AI calls at scale, serving thousands of dealership customers. The technical challenges include latency, complex state management, AI engineering, and zero tolerance for failure on live customer calls.

What You’ll Do

• We value elegance in simplicity and embrace complex technical decisions together.
• You proactively identify and solve technical problems.
• You apply a first-team mentality — we win and lose as a team.
• You earn trust from others and keep it.
• We value direct communication. No empty corporate-speak.
• Build

• Own services in the live call path — from feature delivery through deployment, monitoring, and incident follow-through.
• Write code across the conversational AI stack: speech-to-text, text-to-speech, Large Language Model (LLM) orchestration, and telephony.
• Build and maintain observability for your services — metrics, structured logs, distributed tracing, and alerts tied to service-level indicators (SLIs) and reliability targets you help define.
• Write Infrastructure as Code using AWS CDK for containerized (ECS) and serverless (Lambda) architectures.
• Build fault-tolerant telephony integrations with graceful degradation, retry logic, and error handling.
• Deliver real-time conversational voice AI, including low-latency infrastructure.
• We optimise the audio pipeline to ensure delivery of high-quality results.
• We are an AI-first engineering team.
• You implement and iterate on prompts, context management, and LLM provider integration patterns in production — building deeper expertise through daily work.
• Our team moves quickly and confidently by investing in code quality, automated tests, and contributing high-value code review feedback.
• We pursue operational excellence through observability infrastructure.
• We are building toward measuring what we ship with service-level indicators (SLIs) and reliability targets, backed by structured logs, monitoring, and alarming.
• We own our outcomes.

• Keep live customer calls healthy by improving alerting, service health checks, and on-call response for latency issues, call failures, and third-party outages.
• Participate in incident response and lead blameless post-mortems for issues in your area — root-cause analysis, corrective actions, and follow-through.
• This role includes on-call responsibilities; the team shares a rotation with escalation support from senior engineers.
• Improve release workflows so changes to call handling, LLM integrations, and customer-facing services deploy safely and roll back quickly.
• Monitor and reduce spend across model providers, telephony usage, and AWS workloads without degrading latency or call quality.
• Own operational posture, on-call practices, and incident follow-through within the team.
• Collaborate with AI Engineers on model integration and optimisation work.
• Communicate incident status and delivery progress clearly to the engineering and product teams.

• Drive small cross-cutting projects — a new telephony integration, a reliability improvement in the call path, or a migration between model providers.
• Participate in systems design decisions for services you own, contributing to choices around latency, fallbacks, provider routing, and failure handling in real-time voice workflows.
• Design and implement maintainable, scalable, and business-aligned systems within your service area, working across modern and legacy components as needed.
• Review changes for operational safety, latency impact, and failure handling — not just code style.
• Reinforce engineering standards and best practices in code reviews and design discussions.
• Translate scoped business requirements into technical solutions within your services.
• Work independently on scoped problems, apply established patterns, and elevate higher-risk design decisions for review.

• Provide insightful code reviews that raise team quality.
• Invest in the success of other team members.
• Help engineers at all levels build technical skills — particularly peers and SDE-Is working in your area.
• You will be especially called upon to help less experienced engineers grow.
• Champion knowledge sharing via documentation, talks, and pairing sessions.

Requirements

• Computer science degree (or equivalent practical experience with data structures, systems, and distributed computing).
• 3+ years building and operating production backend systems.
• Proficient in TypeScript and Node.js.
• AWS experience (ECS, Lambda, SQS, CloudWatch, networking basics).
• Infrastructure as code experience; CDK preferred, willingness to work in CDK required.
• Production database experience (Postgres).
• Experience owning live services in production — deployment, monitoring, observability, and incident response.
• Experience with CI/CD pipelines, automated testing, and on-call operations.
• Track record of debugging and resolving production incidents under time pressure.

Our Ideal Candidate

• Thrive on feedback, coaching, and continuous professional development.
• Are self-motivated, adaptable, and take a curious approach to problem-solving.
• Communicate clearly during delivery and incidents, with a customer-first mindset.
• Work effectively amid ambiguity — debate decisions directly, then commit fully.
• Have experience with real-time systems (WebSockets, event-driven architectures, strict latency requirements).
• Strong backend engineers with adjacent low-latency production experience can ramp with team support.
• Have experience with LLM application development (prompt engineering, context management, latency optimisation).
• Have exposure to telephony or VoIP systems (SIP, RTP, audio codecs).
• Have experience with distributed systems and performance optimisation under latency constraints.
• Have experience with third-party integrations (dealership management systems, scheduling platforms, CRMs).

What’s in It for You?

• Competitive salary package (immediate PTO).
• Full benefits package.
• Fidelity 401k with company match.
• Fun perks including a monthly gym reimbursement, a monthly wellness reimbursement, and a monthly reading allowance.
• Opportunities for continued career growth within the organisation.
• Fun and collaborative work environment.

Call Box is an equal opportunity employer. We evaluate all applicants without regard to race, colour, religion, sex, sexual orientation, gender identity, national origin, disability, veteran status, or any other protected characteristic. If you need accommodations during the application or interview process, let us know.