SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 225,000 - 350,000 / annual
Positron AI is building high-performance systems for production AI inference. The company's Upstack Engineering organization turns accelerator hardware into reliable, scalable services. You will lead the Serving/API team, which owns the software layer between a customer's API request and the tokens Positron accelerators generate.
The Serving/API team is responsible for:
- OpenAI-compatible serving layer: HTTP endpoints, request validation, SSE streaming, usage accounting, and API-spec fidelity
- Tokenization and chat templates: HuggingFace tokenizers, chat-template rendering, and model-specific conversation formats
- Tool calling and structured output: tool-schema handling, tool-call parsing and serialization, and grammar-constrained decoding (llguidance) for JSON and function calls
- Reasoning and budgets: reasoning-channel parsing, reasoning-effort controls, token limits, and per-request budgets
- Speculative decoding: request-side plumbing for draft models and draft trees, acceptance metrics, and policies for when speculation pays off
- New modalities and frameworks: vision-language model (VLM) input handling and integration paths with SGLang-style serving
As Engineering Manager, you will lead, coach, and grow a team of engineers spanning API serving, tokenization, structured generation, and model integration. You will establish a clear technical and organizational roadmap for the serving layer, ensure API fidelity and OpenAI-compatible behavior, lead reasoning-model support and request budgets, and partner with the Compiler/Executor team on speculative decoding. You will lead the plan for VLM support and SGLang interoperability, keep serving-layer overhead off the critical path for latency, and ensure the API layer remains independent of hardware topology as Positron scales. You will work with Production Platform and Orchestration to define clear ownership of shared infrastructure, build release gates and regression suites, and translate customer and business priorities into technical decisions.
This is a technical leadership role with real product accountability. You will set direction, build the team, create clear ownership, and improve the systems behind API fidelity, tool calling, reasoning, speculative decoding, and new-model readiness. You will work closely with Production Platform and Orchestration, Compiler/Executor, hardware, and customer-facing partners.
REQUIREMENTS:
The posting does not explicitly state formal requirements such as years of experience, required education, or specific certifications. However, the role description emphasizes the need for candidates who combine systems depth with organizational judgment, moving comfortably between architecture, delivery, incidents, people development, and cross-functional planning. Experience with distributed systems, model-serving infrastructure, production operations, and team leadership is implied by the scope of responsibilities.
