Software Engineer, AI - 12 month Contract

Transition proof-of-concept prototypes to production-grade systems, managing auth, data persistence, CI/CD pipelines, infrastructure, test suites, and operational runbooks

Design, build, and maintain scalable backend services and RESTful APIs

Architect systems for high availability, reusability, and fault tolerance using retries, circuit breakers, timeouts, and automated fallback mechanisms

Establish strict guardrails to enforce response accuracy, catalog constraints, cost ceilings, and compliance with brand guidelines

Implement end-to-end LLM telemetry and observability (e.g., Langfuse) to track prompts, token usage, latency, spend, and user sessions

Develop multi-tier caching strategies across responses, embeddings, and media to minimize latency and redundant API expenditure

Integrate multimodal generative AI workflows into production pipelines, managing queues, rate limits, and graceful degradation paths

Deploy and optimize cloud infrastructure (AWS/GCP), overseeing secret management, storage, compute resources, and cost management

Drive code quality and reliability through automated unit and integration testing delivered via continuous integration pipelines

Maintain system health and production uptime through comprehensive logging, metrics, tracing, and on-call rotation support

Author and maintain operational documentation for deployment, incident recovery, and infrastructure spend

Leverage AI developer tools to accelerate delivery while maintaining rigorous engineering, review, and testing standards

Own feature lifecycles end-to-end, from initial release to ongoing post-launch production support

5+ years of demonstrated hands-on track record architecting, running, and maintaining production backend microservices and RESTful APIs

Proven experience hardening quick experimental prototypes into production-grade, highly available systems with robust authentication, storage, and reliability standards

End-to-end technical ownership over software quality, test coverage, and architecture, leveraging AI developer tools to accelerate output without sacrificing engineering rigour

Deep expertise deploying and managing cloud infrastructure on AWS or GCP, including identity management, compute, storage resources, and cost control

Production infrastructure fluency using Docker, CI/CD automated deployment pipelines, environment isolation, networking, and zero-downtime rollback strategies

Commitment to operational excellence and system uptime through strict performance thresholds, automated graceful degradation paths, and resilience design

Experience establishing operational guardrails, response validation schemas, rate limits, retries, multi-tier caching, and fallback mechanisms for external services

Direct experience integrating LLM model inference into live pipelines across text, image, or video multimodal workflows

Track record implementing comprehensive LLM telemetry (e.g., Langfuse) to track prompt metrics, token consumption, latency, and operational spend

Skill in architecting multi-tier caching architectures across memory and disk tiers to minimize API costs and drive down service latency

Readiness to participate in on-call rotation support and drive fast incident recovery for production systems

Hands-on mastery across core technical components of our engineering stack:

High adaptability and agility when mastering new frameworks, technologies, and modern developer tooling

Strong proficiency in Python or Node.js backend development (Go experience welcomed)

Experience with relational databases (Postgres), vector search indexes, and caching systems (Redis)

Building scalable API services using modern web frameworks like FastAPI

Containerized deployments with Docker and orchestration platforms like Kubernetes

Cloud platform operations across major ecosystems including AWS and GCP

Delivering continuous integration and delivery pipelines via automated build tooling

Driving software reliability through continuous automated unit, integration, and end-to-end testing

Sufficient frontend expertise (React, JavaScript) to author and maintain internal tooling dashboards

Solid comprehension of the generative AI application development lifecycle

Familiarity serving open-source ML models via engines like vLLM or llama.cpp

Bachelor's degree in Computer Science, Software Engineering, or equivalent practical industry background

Demonstrated passion for hardening production-grade services serving active end users beyond initial experimental prototypes

Rigorous commitment to test coverage prior to deployment, with proven experience executing zero-downtime, stress-free rollback strategies if necessary

Ability to demonstrate full technical ownership moving local proofs-of-concept into live RESTful APIs with auth, multi-tier caching, telemetry, fallbacks, and runbooks

Proven capability optimizing multimodal text and video generative workflows to satisfy strict cost ceilings and latency thresholds via queues, caching, and timeouts

Exceptional cross-functional communication skills, fostering seamless collaboration across engineering and product stakeholders

Pragmatic, hands-on orientation combined with an uncompromising commitment to engineering standards and complete code ownership

High energy, collaborative spirit, and a relentless focus on shipping impactful business results