2 days ago

Member of Technical Staff

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 6 hours agoStatus: Live

Job Summary

Work on performance research and engineering to make inference infrastructure faster, cheaper, and more reliable. Identify gaps between theoretical and production hardware performance, trace latency/throughput regressions from the API layer down to kernels, and optimize batching, scheduling, routing, quantization, and distributed execution. Build benchmarks and observability, validate correctness and model quality, and ship highest-impact fixes with founders on a small team.

Location: San Francisco

Workplace: Onsite

Employment Type: Full time

Job Function: Software Engineering

Seniority: Mid level

Key Responsibilities

•Find the gap between theoretical hardware performance and production performance.
•Trace latency and throughput regressions from the API layer to individual kernels.
•Optimize batching, scheduling, routing, quantization, and distributed execution.
•Build benchmarks and observability to surface bottlenecks.
•Validate optimizations preserve model quality and correctness, and ship high-impact fixes.

Pay and Benefits

Salary: USD 175,000 - 350,000 annually

Equity and Bonus:Equity

Key Requirements

•Have optimized complex production systems.
•Understand GPU performance, memory bandwidth, and collectives for inference serving.
•Be strong in Python and comfortable navigating unfamiliar codebases.
•Turn profiling data into clear engineering decisions.
•Care about tokens per second, tokens per dollar, and correctness equally.

Experience:6+ yearsMachine learningInference serving

Tech Stack:Python

Eligibility

Work Authorization:Authorization required. Sponsorship not provided.

Company Brief

Morph

Provides tools and infrastructure for running, managing, and deploying large language models, offering model orchestration, privacy-preserving inference, and integrations to help developers deploy custom LLMs in production.

Industry: AI & Machine Learning

Growth: Early Stage Startup

Website

Loading job details...

Preparing the role view and application actions.

Morph

2 days ago

Member of Technical Staff

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 6 hours agoStatus: Live

Job Summary

Location: San Francisco

Workplace: Onsite

Employment Type: Full time

Job Function: Software Engineering

Seniority: Mid level

Key Responsibilities

•Find the gap between theoretical hardware performance and production performance.
•Trace latency and throughput regressions from the API layer to individual kernels.
•Optimize batching, scheduling, routing, quantization, and distributed execution.
•Build benchmarks and observability to surface bottlenecks.
•Validate optimizations preserve model quality and correctness, and ship high-impact fixes.

Pay and Benefits

Salary: USD 175,000 - 350,000 annually

Equity and Bonus:Equity

Key Requirements

•Have optimized complex production systems.
•Understand GPU performance, memory bandwidth, and collectives for inference serving.
•Be strong in Python and comfortable navigating unfamiliar codebases.
•Turn profiling data into clear engineering decisions.
•Care about tokens per second, tokens per dollar, and correctness equally.

Experience:6+ yearsMachine learningInference serving

Tech Stack:Python

Eligibility

Work Authorization:Authorization required. Sponsorship not provided.

Company Brief

Morph

Industry: AI & Machine Learning

Growth: Early Stage Startup

Website