AGENTIC SOFTWARE ENGINEER

SvitlaSystems Inc. is looking for anAgentic Software Engineerfor a full-time position (40 hours per week) in the office at Hudson Yards, New York, the USA. You'llbuildthe dataplatforms, infrastructure, and data products that enable investment professionals and business users to create AI-powered workflows and applications safely. The role's core mission is to build the data platform, APIs, workflow infrastructure, and self-serve tooling that make AI useful across the organization. You will create the foundations that let non-developers work with AI in a fast, secure, reliable, and scalable way, including curated data products and APIs, workflow frameworks, application scaffolding, and controlled interfaces to internal data and services. This role also requires a modern engineering mindset. The ideal candidate is excited by the emerging world of agentic engineering and harness engineering, where engineers direct multiple AI agents to produce high-quality production code at high velocity. The perfect candidate combines strong technical execution, solid software design and coding principles, data pipeline construction, and sharp product intuition, with a proven ability to ship independently and at high velocity. Requirements Strong understanding of software engineering with experience building production backend systems, platforms, or data infrastructure. Proven experience in system design and architecture for large-scale or business-critical platforms. Understanding of building APIs, services, data pipelines, or workflow infrastructure. Understanding of modern cloud architecture (AWS or other clouds), distributed systems, and platform operations. Strong knowledge of Python and SQL. Experience building data products, internal platforms, or self-serve infrastructure for technical or non-technical users. Deep curiosity about AI-native development and enthusiasm for working in a world where multiple agents are part of the engineering loop. Hands-on experience building pipelines that integrate real-time and batch data sources across structured and unstructured formats. Experience with LLM applications, vector database, graph databases, retrieval systems, semantic search, AI orchestration, and multi-agent frameworks. Entrepreneurial, high-energy individual with eagerness to operate with high urgency, ownership, and creativity in a fast-moving environment. Strong problem-solving and analytical skills, with the ability to synthesize complex, multi-source data into clear, actionable outputs. Excellent communication and interpersonal skills with the ability to translate technical findings into formats appropriate for PMs, risk officers, and traders. Demonstrated ability to manage multiple workstreams, prioritize under pressure, and meet deadlines in a fast-moving investment environment. Ability to work independently and as part of a cross-functional team spanning many business teams, including Investment, Data Science, Risk, and Trading. Responsibilities Build the AI-Native Data Platform: Design and build the core data platform that powers AI applications, analytics, and operational workflows. Develop secure, scalable, reliable, and discoverable data products for both humans and AI systems. Create data access patterns that are easy to use, safe by default, and robust at scale. Build and maintain APIs and service layers on top of internal data to support downstream applications, automation, and AI workflows. Contribute to semantic and application-facing data layers so users can interact with clean, business-meaningful abstractions rather than raw source systems. Enable Non-Developers to Build with AI: Build platform capabilities that allow investment staff and business users to create AI-powered applications and workflows without requiring deep engineering support. Design safe self-serve patterns for prompt-backed workflows, retrieval-based apps, internal copilots, structured automation, and task‑specific AI tools. Create reusable templates, connectors, workflow abstractions, approval steps, permissions models, and operational guardrails. Ensure these capabilities are secure, observable, auditable, and easy to adopt. Build APIs, Workflows, and Application Infrastructure: Develop APIs and backend services that expose internal data and business logic for use by internal apps, agents, and workflows. Build workflow engines and orchestration layers that combine data retrieval, business rules, model calls, and human review where needed. Design systems that support asynchronous, long‑running, and stateful business processes. Create reusable platform primitives so teams can assemble AI‑enabled use cases quickly without rebuilding infrastructure from scratch. Practice High‑Leverage Agentic Engineering: Use modern AI‑native development workflows to accelerate engineering output dramatically from 10x to 100x. Operate effectively in an environment where engineers direct multiple agents in parallel for coding, testing, refactoring, documentation, and debugging. Use these methods to ship production code quickly and continuously while maintaining quality. We offer US and EU projects based on advanced technologies. Competitive compensation based on skills and experience. Flexibility in workspace, either remote or our welcoming office. Bonuses for article writing, public talks, and other activities. Free tech webinars and meetups organized by Svitla. Regular corporate online activities. Awesome team, friendly and supportive community! Svitla is proud to be an equal opportunity employer. Allqualified applicants will receive consideration for cooperation without regard to age, gender identity, sexual orientation, religion, race, color, national origin, disability, or any other characteristic protected by applicable law. #J-18808-Ljbffr Svitla Systems