Software Architect
Designs and implements intelligent document processing and agentic evaluation frameworks for healthcare AI platform, owning architecture from APIs to production code. Requires 10+ years experience with Python/Scala, LLM integration, and scalable systems.
About the job
What You'll Do
- Own the architecture of Machinify's intelligent document processing platform and agentic evaluation framework — from API design to implementation
- Design abstractions and interfaces that enable agentic workflows to reason over medical records, claims data, and unstructured healthcare documents
- Define the boundaries between orchestration, retrieval, LLM interaction, and domain logic — creating a framework that is principled yet pragmatic. Ensure the system scales.
- Write performant production code — this is a hands-on role where you lead through implementation, not solely through design documents.
- Make foundational technology decisions around prompt architecture, multi-modal LLM integration, RAG patterns, and workflow orchestration
- Drive reliability and observability into AI systems that must operate at healthcare-grade standards
- Collaborate closely with Data Science, Data Engineering, and Product teams to translate complex domain requirements into clean system design
- Reduce technical debt and establish architectural patterns that scale with the platform
- Mentor engineers on system design, API design, and building production-grade AI systems
What We're Looking For
- 10+ years of software engineering experience with a proven track record of owning system architecture at scale
- Experience with Python & Scala/Java — deep experience designing Python-based frameworks and writing idiomatic, well-structured APIs in Python and Scala/Java.
- Demonstrated ability to design effective abstractions: knowing when to generalize, when to keep things concrete, and where to draw boundaries in complex systems
- Experience architecting agentic or multi-step reasoning systems that integrate LLMs into production workflows — framework-agnostic design thinking is valued over familiarity with any specific tool
- Strong background in designing large-scale systems that process unstructured data such as documents, medical records, and images
- Deep understanding of API design principles and building platforms that other engineers build upon
- Proven ability to productionize AI/ML systems with a focus on reliability, observability, and maintainability
- Strong experience with designing with system performance and scaling trade-offs in mind
- Strong CS fundamentals — data structures, distributed systems, asynchronous programming
- Bachelor's or Master's degree in Computer Science, or equivalent experience
Nice to Have
- Experience with Spark, Flink, Kafka, Airflow, or Ray
- Knowledge of Prometheus, Grafana, and observability tooling
- Background in healthcare, fintech, or other regulated industries
- Cross-functional collaboration experience with data scientists and ML engineers
What We Offer
- Competitive salary, 401(k) with company match
- Unlimited PTO
- Additional health and wellness benefits and perks
Skills
Python, Scala, Java, LLMs, RAG, API Design, Distributed Systems, Prompt Engineering, Workflow Orchestration, Observability, Spark, Flink, Kafka, Airflow, Ray
Similar jobs
Backend Engineering jobsStaff Software Engineer leading backend and data-intensive systems, including scalable services, AI-powered workflows, cloud infrastructure, and reliability initiatives. Requires 8+ years of software engineering experience and expertise in distributed systems, data processing, and containerized applications.
Leads the design and implementation of scalable distributed data pipelines and related infrastructure, while improving performance, reliability, and security. Requires 5+ years of software experience, systems programming expertise, cloud and containerization experience, and senior staff-level technical leadership.
Leads performance engineering for high-volume data systems by diagnosing bottlenecks, designing improvements, and building resilient performance platforms. Requires 10+ years of software experience, strong Java and database expertise, and experience with distributed backend systems.
Staff Software Engineer on Snowflake’s Snowtrail team, designing and operating query-processing and distributed infrastructure that improves engineering velocity and production quality. Requires expertise in databases, query optimization, compiler implementation, and large-scale systems.
Staff Software Engineer responsible for the reporting data model, customer-facing data delivery APIs and pipelines, and revenue-critical usage metering and billing systems. The role requires 8+ years of backend and data-systems experience, strong SQL and API expertise, and technical leadership across teams.