Member of Technical Staff - Evals Research Engineer

NeoSigma Telecom Solutions Private Limited•San Francisco, CA

About The Position

NeoSigma is seeking a Backend Engineer to own systems that ingest, evaluate, and serve agent behavior data at production scale. The work spans telemetry ingestion, platform reliability, sandbox infrastructure, and APIs for customers and integrations. The role combines distributed systems and query performance work with customer-facing features across backend services, APIs, and the data layer. The position focuses on designing evaluation frameworks for agentic systems and researching agent evaluation, reward modeling, reward-hacking, post-training, and self-improving systems. The engineer will develop rubrics, verifiers, reward signals, and benchmarks to measure agent performance, reliability, and generalization; own research streams end-to-end; build infrastructure to deliver working systems; and publish findings through technical blogs, papers, and open-source contributions. As a founding team member, the hire will help define NeoSigma’s technical foundation. Scope may grow to include ownership of core systems, architecture, hiring, and engineering culture, with a path toward technical leadership or engineering management as the team scales.

Requirements

  • Strong foundations in machine learning, deep learning, and computer science.
  • Hands-on experience with LLM evaluation, agentic systems, reinforcement learning, or post-training.
  • Strong programming skills in Python and experience building reliable ML research infrastructure.
  • Strong research judgment and the ability to identify and solve complex, meaningful problems.
  • Comfort navigating open-ended research problems and quickly translating ideas into working implementations.
  • High standards for experimental rigor, engineering quality, and clear technical communication.
  • Ability to move quickly and work with high agency.

Responsibilities

  • Design and build evaluation frameworks for agentic systems.
  • Research methods for agent evaluation, reward modeling, reward-hacking, post-training, and self-improving systems.
  • Develop rubrics, verifiers, reward signals, and benchmarks to measure agent performance, reliability, and generalization.
  • Own research streams end-to-end and build infrastructure to ship working systems.
  • Publish research findings through technical blogs, papers, and open-source contributions.
  • Own systems for ingesting, evaluating, and serving agent behavior data at production scale.
  • Work across telemetry ingestion, platform reliability, sandbox infrastructure, and APIs for customers and integrations.
  • Build backend, API, and data-layer features, including work on distributed systems and query performance.
  • Help define the company’s technical foundation and, as the team scales, contribute to architecture, hiring, and engineering culture.

Benefits

  • Competitive salary plus meaningful equity package.
  • Comprehensive medical benefits.
  • Generous PTO.
  • Flexible work arrangements.
  • Direct impact on company direction and technical decisions.
  • High ownership and the opportunity to make a career-defining impact.
  • Visa sponsorship.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service