Senior Software Engineer Applied AI

Job Description

Senior Software Engineer Applied AI Voice Agents \& ML Systems AMC Health Remote US Full time The pitch We build and operate production AI voice agents that hold real phone conversations in a regulated healthcare setting plus the machine learning and LLM pipelines around them This is one seat that spans four disciplines that rarely come together real time systems LLM engineering traditional machine learning and serious cloud infrastructure all in production all with real consequences If you are the kind of engineer who gets restless doing one thing this role is the opposite problem What youll work across Real time voice AI Streaming low latency speech to speech systems built on modern LLMsTelephony and real time media call control live audio streamingAudio handling and the quirks of real human conversation interruptions timing noiseConcurrency on a latency sensitive path where p99 matters and a stall is something a caller hearsLLM engineering Wrapping nondeterministic models in deterministic control so they behave reliably in productionMulti model pipelines prompt design and costlatency budgetingEvaluation harnesses including LLM as judge and automated agent tests agent approachesAgentic tooling that gives AI systems safe structured access to infrastructureTraditional non LLM machine learning End to end ML pipelines feature engineering model training and scheduled inferenceImbalanced messy real world data; calibration and explainability for non technical consumersTurning research notebooks into reproducible auditable production pipelinesCloud and infrastructure Infrastructure as code across multiple environments we run on AWSManaged compute data streaming and orchestration servicesSecurity engineering in a regulated setting encryption least privilege access strict data handling disciplineObservability and telemetry driven debugging tracing a production issue from a metric anomaly to root causePlus occasional full stack work on internal tools and an engineering workflow that leans heavily on AI coding assistants with human accountability for every change What youll actually do Ship and debug code on a live real time voice pipeline where latency and correctness are user facingDesign control systems around LLMs guardrails budgets watchdogs safe fallbacksBuild and operate LLM evaluation and batch analysis pipelinesOwn traditional ML workflows from data to scheduled production inferenceTrace production issues from a metric anomaly to root cause including building the evidence when the cause is a vendorMust haves 7 years building and operating production backend systems with strong general purpose programming skills we work primarily in PythonExperience running distributed systems in the cloud; comfortable debugging from telemetry to root causeHands on production experience with LLMs or generative AI any provider or framework plus the judgment to know when not to use a modelWorking fluency across the traditional machine learning lifecycle you productionize; you do not need to publishDisciplined in a regulated environment small reviewable changes and careful handling of sensitive dataNice to haves Real time media or telephony experienceFront end full stack abilityML pipeline experience vector search or embeddingsFluency with AI coding assistants our workflows assume them with human accountability for every changeHow we work Smallest correct change wins Every behavior change is validated against the live system Evidence over opinion in debugging Code review is rigorous Safety and privacy gate everything Work authorization no exceptions This role is open only to US citizens and lawful permanent residents Green Card holders We cannot consider candidates who require visa sponsorship now or in the future and we are unable to make exceptions of any kind How to apply Please submit both of the following Your LinkedIn profile URLA phone number where we can reach youA resume is welcome but optional; the two items above are required