Senior Software Engineer, LLM Platform

Senior LLM Platform EngineerHandshake is hiring a Senior LLM Platform Engineer to join our Data and ML Platform team. This team supports Handshake's core career marketplace and Handshake AI (HAI) by building the shared data, ML, and LLM infrastructure behind production workflows.This infrastructure-heavy role primarily owns our shared LLM control plane: LiteLLM gateways, provider integrations, shared clients, access controls, observability, cost attribution, capacity management, and hosted or self-hosted inference. You'll also contribute to adjacent platform systems for workflow orchestration, model serving, shared cloud infrastructure, and developer enablement—working closely with Backend Platform, HAI engineering, data science, and FDEs.What You'll DoBuild and operate our LiteLLM-based AI gateways and shared LLM clients.Own provider and model onboarding, routing, failover, rate limits, and capacity planning.Build self-service virtual-key, model-access, budget, and credential-management workflows.Establish SLOs, observability, cost attribution, and alerts for production LLM traffic.Safely qualify and roll out new models, providers, SDKs, and gateway configurations.Support hosted and self-hosted inference through a consistent platform interface.Partner with product, AI, and FDE teams to turn recurring delivery problems into paved-platform capabilities.Contribute to the broader Data and ML Platform, including workflow orchestration, model serving, shared cloud infrastructure, and developer tooling.Participate in team on-call and support, improving runbooks, automation, and reliability across owned platform services.What We're Looking ForStrong production software engineering experience in Python, TypeScript, Go, or a similar language.Experience building or operating high-throughput API gateways, proxies, or multi-tenant platform services.Hands-on experience with Kubernetes, Terraform, CI/CD, and production service ownership.Practical experience with LLM provider APIs, including streaming, long-running requests, retries, timeouts, cancellation, and rate limits.Experience with authentication, quotas, credential management, tenant isolation, and auditability.Experience building observability for distributed systems and leading production incident response.Experience with usage metering, cost attribution, capacity planning, or FinOps.Experience with data or ML platform systems such as BigQuery, Airflow, streaming pipelines, model serving, or ML observability.Strong judgment in ambiguous environments and a bias toward simple, reliable systems that scale.Bonus ExperienceLiteLLM, Portkey, or a comparable multi-provider AI gateway.vLLM, Modal, Ray, Triton, PyTorch, or GPU-backed serving.Temporal or another durable-execution system for long-running LLM requests.Evaluation, batch inference, fine-tuning, RL, or other post-training infrastructure.Agent runtimes, sandbox infrastructure, MCP, tool use, or coding-agent infrastructure.Our StackPython, TypeScript, Go, LiteLLM, FastAPI, PostgreSQL, Redis, GCP, Kubernetes, Terraform, Spacelift, BigQuery, Airflow, Dataflow/Beam, Datastream, OpenAI, Anthropic, Gemini, OpenRouter, vLLM, Modal, Anyscale/Ray, Datadog, Arize, Temporal, Cloudflare, and TailscalePerksHandshake delivers benefits that help you feel supported—and thrive at work and in life. The below benefits are for full-time US employees.Ownership: Equity in a fast-growing companyFinancial Wellness: 401(k) match, competitive compensation, financial coachingFamily Support: Paid parental leave, fertility benefits, parental coachingWellbeing: Medical, dental, and vision, mental health support, $500 wellness stipendGrowth: $2,000 learning stipend, ongoing developmentRemote & Office: Internet, commuting, and free lunch/gym in our SF officeTime Off: Flexible PTO, 15 holidays + 2 flex daysConnection: Team outings & referral bonuses