Design, build, and scale Python backend services and agentic LLM workflows for a multi-tenant, regulated enterprise platform. Productionize LLM integrations (Bedrock), ensure security/compliance, implement async orchestration, optimize data layers (Postgres, vector search/RAG), and add observability, real-time eventing, and typed API contracts. Collaborate cross-functionally and drive architecture to production.
Who are we?
Smarsh empowers its customers to manage risk and unleash intelligence in their digital communications. Our growing community of over 6500 organizations in regulated industries counts on Smarsh every day to help them spot compliance, legal or reputational risks in 80+ communication channels before those risks become regulatory fines or headlines. Relentless innovation has fueled our journey to consistent leadership recognition from analysts like Gartner and Forrester, and our sustained, aggressive growth has landed Smarsh in the annual Inc. 5000 list of fastest-growing American companies since 2008.
Smarsh is hiring a senior backend/platform engineer to build and scale agentic AI systems for enterprise use. You will build fast-moving, early-stage Python services that integrate AI capabilities into a production agentic platform. Your scope spans workflow execution, scale, reliability, and platform hardening as we grow.
This is not a generic backend role. The focus is building and designing agentic systems, shipping working software, and solving hard platform problems in a fast-moving AI-native environment. You will join a small, high-velocity cross-functional group and own problems end to end, designing and building from scratch, making fast architectural calls, and driving ideas from whiteboard to working system with a small, high-agency team.
What will you do?
- Drive backend development for AI workflows as part of a collaborative team. Build and evolve Python/FastAPI services powering core agentic workflows and platform capabilities.
- Productionize LLM integrations. Implement systems around Bedrock usage, quotas, retries, failover, cost controls, model configuration, and approval constraints.
- Design for security and compliance. Address customer data handling, tenant isolation, auditability, observability, and secure processing for regulated workloads. Apply auditable data design patterns to ensure AI outputs are traceable, reproducible, and built to withstand regulatory scrutiny.
- Build for scale. We're a nimble team, but our enterprise customers process data at petabyte scale. Help the platform grow to meet that bar through async job orchestration, performance tuning, and data-layer optimization.
- Support multi-tenant architecture. Contribute to tenant-aware services, role-based access, SSO integration, and admin/reporting capabilities.
- Improve platform reliability. Add monitoring, tracing, alerting, and operational tooling for LLM pipelines, workflow execution, and report generation.
- Build real-time capabilities. Design and implement real-time event delivery and pub/sub patterns to support live workflow state, notifications, and agent feedback loops.
- Contribute to technical decisions. Partner on shared services decisions, platform architecture, and integration boundaries across the stack.
- Work across ambiguity. Translate evolving product requirements and non-functional requirements into practical technical solutions with product, architecture, legal, and security stakeholders.
- Champion code quality. Drive strong typing, automated testing, and continuous integration practices that keep the team fast and safe.
- Design typed API contracts. Own the API surface as a product contract: designing clean, schema-driven APIs that support typed client generation and reliable integration across services.
What will you bring?
- Strong Python backend engineering. 7+ years professional software development, including 5+ years building Python services in production. Deep experience with APIs, async processing, background jobs, and workflow orchestration.
- Cloud-native backend experience. AWS experience, ideally with services relevant to secure enterprise workloads (compute, storage, networking, CI/CD, identity, secrets, encryption).
- Production distributed systems. Proven ability to productionize complex backend systems with reliability, observability, retries, throughput, failure handling, and performance tuning.
- Data-intensive system design. Strong knowledge of PostgreSQL, large-scale data processing patterns, indexing, query tuning, and batch/stream tradeoffs. Experience with retrieval-augmented generation (RAG), vector search, and embedding-based systems is required (not a plus).
- Security and compliance mindset. Experience with multi-tenant systems, RBAC, audit logging, secure data handling, and regulated environments.
- Strong ambiguity handling. Ability to work from partial requirements and shape implementation around product and non-functional requirement constraints.
- Agentic workflow engineering. Hands-on experience building LLM-driven workflows: tool-calling, state machines, human-in-the-loop approval patterns, checkpoint/resume, and multi-step agent orchestration. Familiarity with frameworks like LangGraph or equivalent.
- AI-native engineering. Experience working on or alongside AI-native engineering teams, where AI agents are first-class participants in the development workflow, not just productivity tools. Includes hands-on prompt engineering, eval design, and LLM cost optimization: caching strategies, token efficiency, and model selection tradeoffs.
- Product mindset. Bias for shipping, learning from real usage, and making pragmatic tradeoffs grounded in customer problems. Strong Pluses
- LLM / AI platform experience. Bedrock, OpenAI, Anthropic, LangChain/LangGraph, prompt workflows, evals, tool-calling systems. Experience integrating external AI services safely and reliably.
- Identity and access. SSO/SAML/OIDC, enterprise auth patterns.
- Graph-shaped data and entity resolution. Experience with graph-backed data models, entity deduplication, mention linking, and building systems that reason over connected, structured records.
- Observability stack. OpenTelemetry, tracing, metrics, alerting, cost/usage dashboards.
- Regulated communications or compliance domain. Background in systems that handle sensitive communications, audit trails, or data subject to legal or regulatory review is a meaningful differentiator.
- Infrastructure as code. Terraform, feature flags, canary deployments, release strategies.
About our culture
Smarsh hires lifelong learners with a passion for innovating with purpose, humility and humor. Collaboration is at the heart of everything we do. We work closely with the most popular communications platforms and the world’s leading cloud infrastructure platforms. We use the latest in AI/ML technology to help our customers break new ground at scale. We are a global organization that values diversity, and we believe that providing opportunities for everyone to be their authentic self is key to our success. Smarsh leadership, culture, and commitment to developing our people have all garnered Comparably.com Best Places to Work Awards. Come join us and find out what the best work of your career looks like.
Similar Jobs
Digital Media • Fintech • Information Technology • Machine Learning • Financial Services • Cybersecurity • Automation
Handle inbound and outbound mortgage collections calls, review account status, collect payments, evaluate customer finances, negotiate repayment solutions, and document account actions. Ensure compliance with customer information security, debt collection, and mortgage regulations while meeting quality, productivity, and operational targets. The role includes extensive training and operates on a hybrid schedule with three days onsite and two days remote in Irving, Texas.
Top Skills:
Ai SimulationsDigital Phone SystemsExcelMicrosoft WordMsp/Black Knight
Artificial Intelligence • Fintech • Insurance • Marketing Tech • Software • Analytics
Leads a specialized casualty claims team managing severe-exposure portfolios, complex litigation, coverage issues, reserves, settlements, vendors, and claim-handling protocols. Partners with legal, underwriting, actuarial, reinsurance, and other stakeholders to develop strategies, monitor litigation trends, address legal system abuse, manage financial outcomes, and improve operational performance. Coaches claims leaders, oversees staffing and portfolio capacity, and presents strategic recommendations to executives and business partners.
Top Skills:
Guidewire Claims System
Artificial Intelligence • Fintech • Insurance • Marketing Tech • Software • Analytics
Own model observability for Auto Physical Damage data science products, including traditional ML and GenAI/LLM systems. Build monitoring pipelines, dashboards, metrics, thresholds, alerts, and remediation documentation. Detect drift, performance degradation, anomalies, and data-quality issues; support MLOps, LLMOps, governance, compliance, and audit reporting. Analyze business outcomes, identify improvement opportunities, and communicate model health findings to technical and non-technical stakeholders.
Top Skills:
AWSAzureEmblemExcelGCPLlmopsMlopsPowerPointPythonSASSQLStreamlitTableauVBA
What you need to know about the Austin Tech Scene
Austin has a diverse and thriving tech ecosystem thanks to home-grown companies like Dell and major campuses for IBM, AMD and Apple. The state’s flagship university, the University of Texas at Austin, is known for its engineering school, and the city is known for its annual South by Southwest tech and media conference. Austin’s tech scene spans many verticals, but it’s particularly known for hardware, including semiconductors, as well as AI, biotechnology and cloud computing. And its food and music scene, low taxes and favorable climate has made the city a destination for tech workers from across the country.
Key Facts About Austin Tech
- Number of Tech Workers: 180,500; 13.7% of overall workforce (2024 CompTIA survey)
- Major Tech Employers: Dell, IBM, AMD, Apple, Alphabet
- Key Industries: Artificial intelligence, hardware, cloud computing, software, healthtech
- Funding Landscape: $4.5 billion in VC funding in 2024 (Pitchbook)
- Notable Investors: Live Oak Ventures, Austin Ventures, Hinge Capital, Gigafund, KdT Ventures, Next Coast Ventures, Silverton Partners
- Research Centers and Universities: University of Texas, Southwestern University, Texas State University, Center for Complex Quantum Systems, Oden Institute for Computational Engineering and Sciences, Texas Advanced Computing Center
